{"providers":{"deepinfra":{"id":"deepinfra","name":"Deep Infra","doc":"https://deepinfra.com/models","display_name":"Deep Infra","models":[{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"tencent/Hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":128000},"status":"deprecated","cost":{"input":0.13,"output":0.53,"cache_read":0.033},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/Hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"Llama 3.3 70B Turbo","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.1,"output":0.32},"display_name":"Llama 3.3 70B Turbo","type":"chat"},{"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","name":"Llama 4 Scout 17B","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":327680,"output":16384},"cost":{"input":0.1,"output":0.3},"display_name":"Llama 4 Scout 17B","type":"chat"},{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"Llama 4 Maverick 17B FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"status":"deprecated","cost":{"input":0.2,"output":0.8},"display_name":"Llama 4 Maverick 17B FP8","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2.6-Pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.43,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"status":"deprecated","cost":{"input":1,"output":3,"cache_read":0.2},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"XiaomiMiMo/MiMo-V2.6-Flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"status":"deprecated","cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat"},{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.08,"output":0.16},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT","type":"chat"},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.15},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT","type":"chat"},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.1},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B IT","type":"chat"},{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.07,"output":0.34},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"google/gemma-4-E4B-it","name":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"status":"deprecated","cost":{"input":0.02,"output":0.1},"canonical_model_id":"google/gemma-4-E4B-it","display_name":"Gemma 4 E4B IT","type":"chat"},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":2.5,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.09,"output":1.1},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct","type":"chat"},{"id":"Qwen/Qwen3.7-Max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"tiers":[{"input":5,"output":15,"cache_read":1,"tier":{"type":"context","size":32000}},{"input":6.25,"output":18.5,"cache_read":1.25,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"alibaba/qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","type":"chat"},{"id":"Qwen/Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":1.65,"output":4.951,"cache_read":0.206},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.26,"output":2.6},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.1,"output":0.95,"cache_read":0.1},"display_name":"Qwen3.6 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","name":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":0.3,"output":1,"cache_read":0.1},"display_name":"Qwen3 Coder 480B A35B Instruct Turbo","type":"chat"},{"id":"Qwen/Qwen3-Max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"status":"deprecated","cost":{"input":1.2,"output":6,"cache_read":0.24,"tiers":[{"input":2.4,"output":12,"cache_read":0.48,"tier":{"type":"context","size":32000}},{"input":3,"output":15,"cache_read":0.6,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.09,"output":0.55},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen3.8-Flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.113,"output":0.382,"cache_read":0.0141},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.08,"output":0.28},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-01","last_updated":"2026-04-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.14,"output":1,"cache_read":0.05},"display_name":"Qwen 3.5 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.29,"output":2.4},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.15},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen 3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-01","last_updated":"2026-04-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.45,"output":3,"cache_read":0.22},"display_name":"Qwen 3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"status":"deprecated","cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.5},"canonical_model_id":"alibaba/qwen3-30b-a3b","display_name":"Qwen3 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.32,"output":3.2},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.25,"output":0.95,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek-V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.06,"output":0.18,"cache_read":0.015},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.2,"output":0.6,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":0.09,"output":0.18,"cache_read":0.018},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":64000},"cost":{"input":0.26,"output":0.38,"cache_read":0.13},"display_name":"DeepSeek-V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":64000},"cost":{"input":0.5,"output":2.15,"cache_read":0.35},"display_name":"DeepSeek-R1-0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.2,"output":0.6,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.32,"output":0.89},"canonical_model_id":"deepseek/deepseek-v3","display_name":"DeepSeek-V3","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"status":"deprecated","cost":{"input":0.24,"output":0.9,"cache_read":0.135},"canonical_model_id":"deepseek/deepseek-v3-0324","display_name":"DeepSeek V3 0324","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"stepfun-ai/Step-3.7-Flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"status":"deprecated","cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"stepfun-ai/Step-5-Preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1000000},"cost":{"input":1,"output":2.7,"cache_read":0.1},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":512000},"cost":{"input":0.28,"output":1.1,"cache_read":0.056},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-06","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"status":"deprecated","cost":{"input":0.15,"output":1.15,"cache_read":0.03},"display_name":"MiniMax M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"status":"deprecated","cost":{"input":0.25,"output":1,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistralai/Mistral-Small-24B-Instruct-2501","name":"Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.05,"output":0.08},"canonical_model_id":"mistral/mistral-small-24b-instruct-2501","display_name":"Mistral Small 3","type":"chat"},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.75,"output":3.5,"cache_read":0.15},"display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2.85,"output":14.25,"cache_read":0.285},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.68,"output":3.4,"cache_read":0.136},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"status":"deprecated","cost":{"input":0.45,"output":2.25,"cache_read":0.07},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"status":"deprecated","cost":{"input":1.05,"output":3.5,"cache_read":0.205},"display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.75,"output":2.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.4,"output":1.75,"cache_read":0.08},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"status":"deprecated","cost":{"input":0.6,"output":2.08,"cache_read":0.12},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.5,"output":2,"cache_read":0.1},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"status":"deprecated","cost":{"input":0.06,"output":0.4,"cache_read":0.01},"display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.9,"output":4,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/Nemotron-3-Nano-30B-A3B","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.05,"output":0.2,"cache_read":0.025},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","name":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0.4,"output":0.4},"canonical_model_id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","display_name":"Llama 3.3 Nemotron Super 49B v1.5","type":"chat"},{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.2,"output":0.8},"canonical_model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","display_name":"Nemotron 3 Nano Omni 30B A3B Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ByteDance/Seed-2.0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1,"tiers":[{"input":1,"output":6,"cache_read":0.2,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code","type":"chat"},{"id":"ByteDance/Seed-2.0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.5,"output":3,"cache_read":0.1,"tiers":[{"input":1,"output":6,"cache_read":0.2,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-pro","display_name":"Seed 2.0 Pro","type":"chat"},{"id":"ByteDance/Seed-2.0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.1,"output":0.4,"cache_read":0.02,"tiers":[{"input":0.2,"output":0.8,"cache_read":0.2,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed 2.0 Mini","type":"chat"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.03,"output":0.14},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.037,"output":0.17},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"perplexity-agent":{"id":"perplexity-agent","api":"https://api.perplexity.ai/v1","name":"Perplexity Agent","doc":"https://docs.perplexity.ai/docs/agent-api/models","display_name":"Perplexity Agent","models":[{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5},"display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.13,"output":0.26,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"perplexity/sonar","name":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.25,"output":2.5,"cache_read":0.0625},"display_name":"Sonar","type":"chat"},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"tiers":[{"input":0.5,"output":3,"cache_read":0.05,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.5,"output":3,"cache_read":0.05}},"display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"xai/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast (Non-Reasoning)","type":"chat"},{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32000},"cost":{"input":0.25,"output":2.5},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot-ai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshot-ai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-07-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"bailing":{"id":"bailing","api":"https://api.tbox.cn/api/llm/v1","name":"Bailing","doc":"https://alipaytbox.yuque.com/sxs0ba/ling/intro","display_name":"Bailing","models":[{"id":"Ring-1T","name":"Ring-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-10","last_updated":"2025-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.57,"output":2.29},"display_name":"Ring-1T","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Ling-1T","name":"Ling-1T","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-10","last_updated":"2025-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.57,"output":2.29},"display_name":"Ling-1T","type":"chat"}]},"poe":{"id":"poe","api":"https://api.poe.com/v1","name":"Poe","doc":"https://creator.poe.com/docs/external-applications/openai-compatible-api","display_name":"Poe","models":[{"id":"cerebras/qwen3-32b-cs","name":"qwen3-32b-cs","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-05-15","last_updated":"2025-05-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"status":"deprecated","display_name":"qwen3-32b-cs","type":"chat"},{"id":"cerebras/llama-3.1-8b-cs","name":"Llama-3.1-8B-CS","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-05-13","last_updated":"2025-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.1,"output":0.1},"display_name":"Llama-3.1-8B-CS","type":"chat"},{"id":"cerebras/llama-3.3-70b-cs","name":"llama-3.3-70b-cs","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-05-13","last_updated":"2025-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"status":"deprecated","display_name":"llama-3.3-70b-cs","type":"chat"},{"id":"cerebras/gpt-oss-120b-cs","name":"GPT-OSS-120B-CS","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.35,"output":0.75},"display_name":"GPT-OSS-120B-CS","type":"chat"},{"id":"cerebras/qwen3-235b-2507-cs","name":"qwen3-235b-2507-cs","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"status":"deprecated","display_name":"qwen3-235b-2507-cs","type":"chat"},{"id":"empiriolabs/deepseek-v4-pro-el","name":"DeepSeek-V4-Pro-EL","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-05-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":1.67,"output":3.33},"display_name":"DeepSeek-V4-Pro-EL","type":"chat"},{"id":"empiriolabs/deepseek-v4-flash-el","name":"DeepSeek-V4-Flash-EL","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-05-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":0.14,"output":0.28},"display_name":"DeepSeek-V4-Flash-EL","type":"chat"},{"id":"anthropic/claude-haiku-3.5","name":"Claude-Haiku-3.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"cost":{"input":0.68,"output":3.4,"cache_read":0.068,"cache_write":0.85},"display_name":"Claude-Haiku-3.5","type":"chat"},{"id":"anthropic/claude-opus-4.1","name":"Claude-Opus-4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":0,"max":31999}],"tool_call":true,"temperature":false,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":32000},"cost":{"input":13,"output":64,"cache_read":1.3,"cache_write":16},"display_name":"Claude-Opus-4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.5","name":"Claude-Opus-4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":0,"max":63999}],"tool_call":true,"temperature":false,"release_date":"2025-11-21","last_updated":"2025-11-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":64000},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.3},"display_name":"Claude-Opus-4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Claude-Opus-4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":128000},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.3},"display_name":"Claude-Opus-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-3.5-june","name":"Claude-Sonnet-3.5-June","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-11-18","last_updated":"2024-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"status":"deprecated","cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"display_name":"Claude-Sonnet-3.5-June","type":"chat"},{"id":"anthropic/claude-opus-4.7","name":"Claude-Opus-4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":128000},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.4},"display_name":"Claude-Opus-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-3","name":"Claude-Haiku-3","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-03-09","last_updated":"2024-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"cost":{"input":0.21,"output":1.1,"cache_read":0.021,"cache_write":0.26},"display_name":"Claude-Haiku-3","type":"chat"},{"id":"anthropic/claude-opus-4.8","name":"Claude-Opus-4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":128000},"cost":{"input":4.2929,"output":21.4646},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude-Opus-4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-3.7","name":"Claude-Sonnet-3.7","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"display_name":"Claude-Sonnet-3.7","type":"chat"},{"id":"anthropic/claude-haiku-4.5","name":"Claude-Haiku-4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":0,"max":63999}],"tool_call":true,"temperature":false,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":64000},"cost":{"input":0.85,"output":4.3,"cache_read":0.085,"cache_write":1.1},"display_name":"Claude-Haiku-4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4.5","name":"Claude-Sonnet-4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":0,"max":31999}],"tool_call":true,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":32768},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"display_name":"Claude-Sonnet-4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4","name":"Claude-Sonnet-4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-05-21","last_updated":"2025-05-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":64000},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"display_name":"Claude-Sonnet-4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-3.5","name":"Claude-Sonnet-3.5","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-06-05","last_updated":"2024-06-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"status":"deprecated","cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"display_name":"Claude-Sonnet-3.5","type":"chat"},{"id":"anthropic/claude-sonnet-4.6","name":"Claude-Sonnet-4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"display_name":"Claude-Sonnet-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4","name":"Claude-Opus-4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-05-21","last_updated":"2025-05-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":192512,"output":28672},"cost":{"input":13,"output":64,"cache_read":1.3,"cache_write":16},"display_name":"Claude-Opus-4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"elevenlabs/elevenlabs-v2.5-turbo","name":"ElevenLabs-v2.5-Turbo","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-10-28","last_updated":"2024-10-28","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"ElevenLabs-v2.5-Turbo","type":"chat"},{"id":"elevenlabs/elevenlabs-v3","name":"ElevenLabs-v3","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"ElevenLabs-v3","type":"chat"},{"id":"elevenlabs/elevenlabs-music","name":"ElevenLabs-Music","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-08-29","last_updated":"2025-08-29","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":2000,"output":8192},"display_name":"ElevenLabs-Music","type":"chat"},{"id":"novita/glm-4.6v","name":"glm-4.6v","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"display_name":"glm-4.6v","type":"chat"},{"id":"novita/glm-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":true,"reasoning":{"supported":true},"tool_call":true,"temperature":false,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/kimi-k2.6","name":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-05-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.96,"output":4.04,"cache_read":0.16},"display_name":"Kimi-K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/kimi-k2-thinking","name":"kimi-k2-thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-11-07","last_updated":"2025-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"display_name":"kimi-k2-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/kimi-k2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"display_name":"Kimi-K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/glm-4.7-flash","name":"glm-4.7-flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":65500},"display_name":"glm-4.7-flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/glm-4.7","name":"glm-4.7","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"status":"deprecated","display_name":"glm-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/glm-4.7-n","name":"glm-4.7-n","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"display_name":"glm-4.7-n","type":"chat"},{"id":"novita/deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.27,"output":0.4,"cache_read":0.13},"display_name":"DeepSeek-V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/minimax-m2.1","name":"minimax-m2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-12-26","last_updated":"2025-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"display_name":"minimax-m2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"lumalabs/ray2","name":"Ray2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ray","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":5000,"output":8192},"display_name":"Ray2","type":"chat"},{"id":"poetools/claude-code","name":"claude-code","description":"Claude model for careful reasoning, writing, coding, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-11-27","last_updated":"2025-11-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"claude-code","type":"chat"},{"id":"google/imagen-3-fast","name":"Imagen-3-Fast","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-10-17","last_updated":"2024-10-17","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Imagen-3-Fast","type":"chat"},{"id":"google/imagen-4-ultra","name":"Imagen-4-Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-05-24","last_updated":"2025-05-24","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Imagen-4-Ultra","type":"chat"},{"id":"google/gemini-deep-research","name":"gemini-deep-research","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":8192},"status":"deprecated","cost":{"input":1.6,"output":9.6},"display_name":"gemini-deep-research","type":"chat"},{"id":"google/imagen-4","name":"Imagen-4","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Imagen-4","type":"chat"},{"id":"google/imagen-4-fast","name":"Imagen-4-Fast","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Imagen-4-Fast","type":"chat"},{"id":"google/lyria","name":"Lyria","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-06-04","last_updated":"2025-06-04","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Lyria","type":"chat"},{"id":"google/nano-banana","name":"Nano-Banana","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"nano-banana","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0.21,"output":1.8,"cache_read":0.021},"display_name":"Nano-Banana","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini-3.6-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.7576,"output":3.7879,"cache_read":0.0758},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini-3.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/veo-3-fast","name":"Veo-3-Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-10-13","last_updated":"2025-10-13","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Veo-3-Fast","type":"chat"},{"id":"google/gemini-2.0-flash","name":"Gemini-2.0-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":990000,"output":8192},"cost":{"input":0.1,"output":0.42},"display_name":"Gemini-2.0-Flash","type":"chat"},{"id":"google/veo-3.1","name":"Veo-3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Veo-3.1","type":"chat"},{"id":"google/nano-banana-pro","name":"Nano-Banana-Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"nano-banana","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":2,"output":12,"cache_read":0.2},"display_name":"Nano-Banana-Pro","type":"chat"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini-3.5-Flash-Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.303,"output":2.5253,"cache_read":0.0303},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini-3.5-Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-2.0-flash-lite","name":"Gemini-2.0-Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-02-05","last_updated":"2025-02-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":990000,"output":8192},"cost":{"input":0.052,"output":0.21},"display_name":"Gemini-2.0-Flash-Lite","type":"chat"},{"id":"google/gemini-omni-1.1-flash","type":"video","name":"Gemini-Omni-1.1-Flash","description":"Video generation and editing model for scene extension, frame interpolation, and reference-guided multimodal control","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":false,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":false,"limit":{"context":131072,"output":57920},"cost":{"input":1.5152,"output":9.0909},"canonical_model_id":"google/gemini-omni-1.1-flash","display_name":"Gemini-Omni-1.1-Flash"},{"id":"google/gemini-3-flash","name":"Gemini-3-Flash","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.404,"output":2.4242,"cache_read":0.0404},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini-3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini-3.5-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5152,"output":9.0909,"cache_read":0.1515},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini-3.5-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini-2.5-Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":0,"max":32768}],"tool_call":true,"temperature":false,"release_date":"2025-02-05","last_updated":"2025-02-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1065535,"output":65535},"cost":{"input":0.87,"output":7,"cache_read":0.087},"display_name":"Gemini-2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini-2.5-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":false,"release_date":"2025-04-26","last_updated":"2025-04-26","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1065535,"output":65535},"cost":{"input":0.21,"output":1.8,"cache_read":0.021},"display_name":"Gemini-2.5-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/imagen-3","name":"Imagen-3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-10-15","last_updated":"2024-10-15","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Imagen-3","type":"chat"},{"id":"google/gemini-3-pro","name":"Gemini-3-Pro","description":"Legacy model retained for compatibility with older integrations","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-10-22","last_updated":"2025-10-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":1.6,"output":9.6,"cache_read":0.16},"display_name":"Gemini-3-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.7-flash","name":"Gemini-3.7-Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.7576,"output":3.7879,"cache_read":0.0758},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini-3.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/veo-2","name":"Veo-2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Veo-2","type":"chat"},{"id":"google/veo-3.1-fast","name":"Veo-3.1-Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Veo-3.1-Fast","type":"chat"},{"id":"google/gemma-4-31b","name":"Gemma-4-31B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":8192},"cost":{"input":0,"output":0},"display_name":"Gemma-4-31B","type":"chat"},{"id":"google/gemini-3.8-flash","name":"Gemini-3.8-Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.7576,"output":3.7879,"cache_read":0.0758},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini-3.8-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/veo-3","name":"Veo-3","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-05-21","last_updated":"2025-05-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Veo-3","type":"chat"},{"id":"google/gemini-2.5-flash-lite","name":"Gemini-2.5-Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":false,"release_date":"2025-06-19","last_updated":"2025-06-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1024000,"output":64000},"cost":{"input":0.07,"output":0.28},"display_name":"Gemini-2.5-Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro","name":"Gemini-3.1-Pro","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2.0202,"output":12.1212,"cache_read":0.202},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini-3.1-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite","name":"Gemini-3.1-Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.2525,"output":1.5152},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini-3.1-Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-3","name":"Grok 3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-04-11","last_updated":"2025-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.75},"display_name":"Grok 3","type":"chat"},{"id":"xai/grok-4.20-multi-agent","name":"Grok-4.20-Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2026-03-13","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2,"output":6,"cache_read":0.2},"display_name":"Grok-4.20-Multi-Agent","type":"chat"},{"id":"xai/grok-4","name":"Grok-4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.75},"display_name":"Grok-4","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4-fast-reasoning","name":"Grok-4-Fast-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-09-16","last_updated":"2025-09-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok-4-Fast-Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.1-fast-reasoning","name":"Grok-4.1-Fast-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"display_name":"Grok-4.1-Fast-Reasoning","type":"chat"},{"id":"xai/grok-4-fast-non-reasoning","name":"Grok-4-Fast-Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-09-16","last_updated":"2025-09-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok-4-Fast-Non-Reasoning","type":"chat"},{"id":"xai/grok-3-mini","name":"Grok 3 Mini","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-04-11","last_updated":"2025-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.3,"output":0.5,"cache_read":0.075},"display_name":"Grok 3 Mini","type":"chat"},{"id":"xai/grok-code-fast-1","name":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-08-22","last_updated":"2025-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.2,"output":1.5,"cache_read":0.02},"display_name":"Grok Code Fast 1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.1-fast-non-reasoning","name":"Grok-4.1-Fast-Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"display_name":"Grok-4.1-Fast-Non-Reasoning","type":"chat"},{"id":"ideogramai/ideogram-v2","name":"Ideogram-v2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-08-21","last_updated":"2024-08-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":8192},"display_name":"Ideogram-v2","type":"chat"},{"id":"ideogramai/ideogram-v2a-turbo","name":"Ideogram-v2a-Turbo","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-02-27","last_updated":"2025-02-27","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":8192},"display_name":"Ideogram-v2a-Turbo","type":"chat"},{"id":"ideogramai/ideogram-v2a","name":"Ideogram-v2a","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-02-27","last_updated":"2025-02-27","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":8192},"display_name":"Ideogram-v2a","type":"chat"},{"id":"ideogramai/ideogram","name":"Ideogram","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-04-03","last_updated":"2024-04-03","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":8192},"display_name":"Ideogram","type":"chat"},{"id":"fireworks-ai/kimi-k2.5-fw","name":"Kimi-K2.5-FW","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":245760,"output":16384},"cost":{"input":0,"output":0},"display_name":"Kimi-K2.5-FW","type":"chat"},{"id":"runwayml/runway","name":"Runway","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"runway","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-10-11","last_updated":"2024-10-11","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":256,"output":8192},"display_name":"Runway","type":"chat"},{"id":"runwayml/runway-gen-4-turbo","name":"Runway-Gen-4-Turbo","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"runway","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-05-09","last_updated":"2025-05-09","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":256,"output":8192},"display_name":"Runway-Gen-4-Turbo","type":"chat"},{"id":"trytako/tako","name":"Tako","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"tako","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":8192},"display_name":"Tako","type":"chat"},{"id":"stabilityai/stablediffusionxl","name":"StableDiffusionXL","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2023-07-09","last_updated":"2023-07-09","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":200,"output":8192},"display_name":"StableDiffusionXL","type":"chat"},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":14,"cache_read":0.22},"display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/dall-e-3","name":"DALL-E-3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"dall-e","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":800,"output":8192},"display_name":"DALL-E-3","type":"image-generation"},{"id":"openai/sora-2","name":"Sora-2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"sora","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Sora-2","type":"chat"},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4-Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":27,"output":160},"display_name":"GPT-5.4-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2023-09-13","last_updated":"2023-09-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":2048},"cost":{"input":0.45,"output":1.4},"display_name":"GPT-3.5-Turbo","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5-Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":27.2727,"output":163.6364},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4-Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.18,"output":1.1,"cache_read":0.018},"display_name":"GPT-5.4-Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.6,"output":13,"cache_read":0.16},"display_name":"GPT-5.2-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex","name":"GPT-5.1-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"display_name":"GPT-5.1-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-4o-search","name":"GPT-4o-Search","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-03-11","last_updated":"2025-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2.2,"output":9},"display_name":"GPT-4o-Search","type":"chat"},{"id":"openai/sora-2-pro","name":"Sora-2-Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"sora","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Sora-2-Pro","type":"chat"},{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9},"display_name":"GPT-5-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-mini","name":"GPT-5-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.22,"output":1.8,"cache_read":0.022},"display_name":"GPT-5-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-image-2","name":"GPT-Image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5.0505,"output":32.3232,"cache_read":1.2626},"display_name":"GPT-Image-2","type":"image-generation"},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":19,"output":150},"display_name":"GPT-5.2-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.99,"output":4,"cache_read":0.25},"display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-01-31","last_updated":"2025-01-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.99,"output":4},"display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-10","last_updated":"2026-02-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.6,"output":13,"cache_read":0.16},"display_name":"GPT-5.3-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.09,"output":0.36,"cache_read":0.022},"display_name":"GPT-4.1-nano","type":"chat"},{"id":"openai/o3-deep-research","name":"o3-deep-research","description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":9,"output":36,"cache_read":2.2},"display_name":"o3-deep-research","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-nano","name":"GPT-5-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.045,"output":0.36,"cache_read":0.0045},"display_name":"GPT-5-nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-instant","name":"GPT-5.2-Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":true,"default":false},"tool_call":true,"temperature":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.6,"output":13,"cache_read":0.16},"display_name":"GPT-5.2-Instant","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2024-12-18","last_updated":"2024-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":14,"output":54},"display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/chatgpt-4o-latest","name":"ChatGPT-4o-Latest","description":"Legacy model retained for compatibility with older integrations","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-08-14","last_updated":"2024-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":4.5,"output":14},"display_name":"ChatGPT-4o-Latest","type":"chat"},{"id":"openai/gpt-5-pro","name":"GPT-5-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":14,"output":110},"display_name":"GPT-5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo-instruct","name":"GPT-3.5-Turbo-Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2023-09-20","last_updated":"2023-09-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":3500,"output":1024},"cost":{"input":1.4,"output":1.8},"display_name":"GPT-3.5-Turbo-Instruct","type":"chat"},{"id":"openai/gpt-5.3-codex-spark","name":"GPT-5.3-Codex-Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"display_name":"GPT-5.3-Codex-Spark","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-chat","name":"GPT-5-Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":9,"cache_read":0.11},"display_name":"GPT-5-Chat","type":"chat"},{"id":"openai/gpt-4o-mini","name":"GPT-4o-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":124096,"output":4096},"cost":{"input":0.14,"output":0.54,"cache_read":0.068},"display_name":"GPT-4o-mini","type":"chat"},{"id":"openai/o3-pro","name":"o3-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":18,"output":72},"display_name":"o3-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.3-instant","name":"GPT-5.3-Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"cost":{"input":1.6,"output":13,"cache_read":0.16},"display_name":"GPT-5.3-Instant","type":"chat"},{"id":"openai/gpt-4o-aug","name":"GPT-4o-Aug","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-11-21","last_updated":"2024-11-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2.2,"output":9,"cache_read":1.1},"display_name":"GPT-4o-Aug","type":"chat"},{"id":"openai/o3-mini-high","name":"o3-mini-high","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-01-31","last_updated":"2025-01-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.99,"output":4},"display_name":"o3-mini-high","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-instant","name":"GPT-5.1-Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":9,"cache_read":0.11},"display_name":"GPT-5.1-Instant","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-image-1","name":"GPT-Image-1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"GPT-Image-1","type":"image-generation"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4-Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-03-12","last_updated":"2026-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.68,"output":4,"cache_read":0.068},"display_name":"GPT-5.4-Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1-Codex-Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"display_name":"GPT-5.1-Codex-Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.6,"output":13,"cache_read":0.16},"display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":4.5455,"output":27.2727,"cache_read":0.4545},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini-deep-research","name":"o4-mini-deep-research","description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.8,"output":7.2,"cache_read":0.45},"display_name":"o4-mini-deep-research","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":1.8,"output":7.2,"cache_read":0.45},"display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4-classic-0314","name":"GPT-4-Classic-0314","description":"Legacy model retained for compatibility with older integrations","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-08-26","last_updated":"2024-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"status":"deprecated","cost":{"input":27,"output":54},"display_name":"GPT-4-Classic-0314","type":"chat"},{"id":"openai/gpt-4-classic","name":"GPT-4-Classic","description":"Legacy model retained for compatibility with older integrations","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-03-25","last_updated":"2024-03-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"status":"deprecated","cost":{"input":27,"output":54},"display_name":"GPT-4-Classic","type":"chat"},{"id":"openai/gpt-4o-mini-search","name":"GPT-4o-mini-Search","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-03-11","last_updated":"2025-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.14,"output":0.54},"display_name":"GPT-4o-mini-Search","type":"chat"},{"id":"openai/gpt-3.5-turbo-raw","name":"GPT-3.5-Turbo-Raw","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2023-09-27","last_updated":"2023-09-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":4524,"output":2048},"cost":{"input":0.45,"output":1.4},"display_name":"GPT-3.5-Turbo-Raw","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.36,"output":1.4,"cache_read":0.09},"display_name":"GPT-4.1-mini","type":"chat"},{"id":"openai/gpt-image-1-mini","name":"GPT-Image-1-Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"GPT-Image-1-Mini","type":"image-generation"},{"id":"openai/gpt-image-1.5","name":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"gpt-image-1.5","type":"image-generation"},{"id":"openai/gpt-4-turbo","name":"GPT-4-Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2023-09-13","last_updated":"2023-09-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":9,"output":27},"display_name":"GPT-4-Turbo","type":"chat"},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1-Codex-Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.22,"output":1.8,"cache_read":0.022},"display_name":"GPT-5.1-Codex-Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3","name":"o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.8,"output":7.2,"cache_read":0.45},"display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":140,"output":540},"display_name":"o1-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"topazlabs-co/topazlabs","name":"TopazLabs","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"topazlabs","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":204,"output":8192},"display_name":"TopazLabs","type":"chat"}]},"cerebras":{"id":"cerebras","name":"Cerebras","doc":"https://inference-docs.cerebras.ai/models/overview","display_name":"Cerebras","models":[{"id":"qwen-3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-09-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":40960},"cost":{"input":0.99,"output":1.49,"cache_read":0.99},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2026-06-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":40960},"cost":{"input":0.35,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"groq":{"id":"groq","name":"Groq","doc":"https://console.groq.com/docs/models","display_name":"Groq","models":[{"id":"whisper-large-v3","name":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2023-09-01","last_updated":"2025-09-05","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"display_name":"Whisper","type":"chat"},{"id":"llama-3.3-70b-versatile","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.59,"output":0.79},"display_name":"Llama 3.3 70B","type":"chat"},{"id":"allam-2-7b","name":"ALLaM-2-7b","description":"ALLaM-2-7b instruction tuned model by SDAIA","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-01-23","last_updated":"2025-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0,"output":0},"canonical_model_id":"sdaia/allam-2-7b","display_name":"ALLaM-2-7b","type":"chat"},{"id":"whisper-large-v3-turbo","name":"Whisper Large V3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"display_name":"Whisper Large V3 Turbo","type":"chat"},{"id":"llama-3.1-8b-instant","name":"Llama 3.1 8B","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.08},"display_name":"Llama 3.1 8B","type":"chat"},{"id":"groq/compound-mini","name":"Compound Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"groq","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"display_name":"Compound Mini","type":"chat"},{"id":"groq/compound","name":"Compound","description":"General-purpose chat model for instruction following, writing, and analysis","family":"groq","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"display_name":"Compound","type":"chat"},{"id":"meta-llama/llama-prompt-guard-2-86m","name":"Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-05-29","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":512},"status":"beta","cost":{"input":0.04,"output":0.04},"display_name":"Prompt Guard 2 86M","type":"chat"},{"id":"meta-llama/llama-prompt-guard-2-22m","name":"Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-05-29","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":512},"status":"beta","cost":{"input":0.03,"output":0.03},"display_name":"Llama Prompt Guard 2 22M","type":"chat"},{"id":"canopylabs/orpheus-v1-english","name":"Canopy Labs Orpheus V1 English","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":4000,"output":50000},"status":"beta","display_name":"Canopy Labs Orpheus V1 English","type":"chat"},{"id":"canopylabs/orpheus-arabic-saudi","name":"Canopy Labs Orpheus Arabic Saudi","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":4000,"output":50000},"status":"beta","display_name":"Canopy Labs Orpheus Arabic Saudi","type":"chat"},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","default","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131042,"output":16384},"cost":{"input":0.8,"output":4},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","default"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.6,"output":3,"cache_read":0.3},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-safeguard-20b","name":"Safety GPT OSS 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2026-06-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"status":"beta","cost":{"input":0.075,"output":0.3},"display_name":"Safety GPT OSS 20B","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-10-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"blueclaw":{"id":"blueclaw","api":"https://openai.blueclaw.network/v1","name":"Blue Claw","doc":"https://blueclaw.network","display_name":"Blue Claw","models":[{"id":"Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"status":"beta","canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"}]},"zai":{"id":"zai","api":"https://api.z.ai/api/paas/v4","name":"Z.AI","doc":"https://docs.z.ai/guides/overview/pricing","display_name":"Z.AI","models":[{"id":"glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"display_name":"GLM-4.6V","type":"chat"},{"id":"glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"display_name":"GLM-4.5","type":"chat"},{"id":"glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"display_name":"GLM-5V-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.6v-flash","name":"GLM-4.6V-Flash","description":"Lightweight GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.6v-flash","display_name":"GLM-4.6V-Flash","type":"chat"},{"id":"glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"display_name":"GLM-4.5V","type":"chat"},{"id":"glm-5.3-flashx","name":"GLM-5.3-FlashX","description":"High-speed GLM-5.3-Flash serving option for coding and agent workflows","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-FlashX","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.5-flash","name":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.5-Flash","type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"display_name":"GLM-4.7-FlashX","type":"chat"},{"id":"glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"display_name":"GLM-4.5-Air","type":"chat"},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"empiriolabs":{"id":"empiriolabs","api":"https://api.empiriolabs.ai/v1","name":"EmpirioLabs AI","doc":"https://docs.empiriolabs.ai","display_name":"EmpirioLabs AI","models":[{"id":"qwen3-8-max-0902","name":"Qwen3.8 Max 0902","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":2},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"qwen3-6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.5,"tiers":[{"input":2,"output":6,"cache_read":2,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":2}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat"},{"id":"qwen3-6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.412564,"output":2.475384,"cache_read":0.412564},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat"},{"id":"glm-5-3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.075,"output":0.25,"cache_read":0.075},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat"},{"id":"kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.95,"output":4,"cache_read":0.95},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat"},{"id":"fugu-max","name":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"sakana/fugu-max","display_name":"Fugu Max","type":"chat"},{"id":"seed-2-0-lite","name":"Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.31,"output":2.5,"cache_read":0.31,"tiers":[{"input":0.62,"output":5,"cache_read":0.62,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-lite","display_name":"Seed 2.0 Lite","type":"chat"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.424,"output":1.272,"cache_read":0.424},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2-5","name":"MiMo V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.7,"output":1.4,"cache_read":0.014},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo V2.5","type":"chat"},{"id":"seed-2-0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.12,"output":0.5,"cache_read":0.12,"tiers":[{"input":0.24,"output":1,"cache_read":0.24,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed 2.0 Mini","type":"chat"},{"id":"muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.8,"cache_read":0.05},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4-7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM 4.7 Flash","type":"chat"},{"id":"mimo-v2-6-pro","name":"MiMo V2.6 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.435},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo V2.6 Pro","type":"chat"},{"id":"qwen3-7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":64000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":2.5},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat"},{"id":"step-3-5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash","type":"chat"},{"id":"qwen3-8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":2},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat"},{"id":"minimax-m2-7-highspeed","name":"MiniMax M2.7 Highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax M2.7 Highspeed","type":"chat"},{"id":"mimo-v2-5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":2.175,"output":4.35,"cache_read":0.018},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro","type":"chat"},{"id":"seed-2-0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.63,"output":3.79,"cache_read":0.63,"tiers":[{"input":1.26,"output":7.58,"cache_read":1.26,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-pro","display_name":"Seed 2.0 Pro","type":"chat"},{"id":"qwen3-5-4b","name":"Qwen3.5 4B","description":"Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-02","last_updated":"2026-03-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.04,"output":0.07,"cache_read":0.02},"display_name":"Qwen3.5 4B","type":"chat"},{"id":"step-5-preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1024000,"output":131072},"cost":{"input":1,"output":2.7,"cache_read":0.05},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"qwen3-5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.086,"output":0.688,"cache_read":0.086,"tiers":[{"input":0.258,"output":2.064,"cache_read":0.258,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat"},{"id":"seed-2-1-turbo","name":"Seed 2.1 Turbo","description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.63,"output":3.13,"cache_read":0.63},"canonical_model_id":"bytedance-seed/seed-2.1-turbo","display_name":"Seed 2.1 Turbo","type":"chat"},{"id":"fugu-ultra-v1-0","name":"Fugu Ultra v1.0","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":7.5,"output":45,"cache_read":1.5,"tiers":[{"input":15,"output":67.5,"cache_read":3,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":15,"output":67.5,"cache_read":3}},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra v1.0","type":"chat"},{"id":"qwen3-5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.115,"output":0.917,"cache_read":0.115,"tiers":[{"input":0.287,"output":2.294,"cache_read":0.287,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat"},{"id":"qwen3-5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.09,"output":0.368,"cache_read":0.09},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash","type":"chat"},{"id":"mimo-v2-6-pro-ultraspeed","name":"MiMo V2.6 Pro UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":4.35,"output":8.7,"cache_read":4.35},"canonical_model_id":"xiaomi/mimo-v2.6-pro-ultraspeed","display_name":"MiMo V2.6 Pro UltraSpeed","type":"chat"},{"id":"glm-5-2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat"},{"id":"mimo-v2-6-flash","name":"MiMo V2.6 Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.14},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo V2.6 Flash","type":"chat"},{"id":"muse-spark-1-2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":1},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat"},{"id":"qwen3-7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991808,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"tiers":[{"input":0.1,"output":0.4,"cache_read":0.02,"tier":{"type":"context","size":32000}},{"input":0.2,"output":0.8,"cache_read":0.04,"tier":{"type":"context","size":256000}}]},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","type":"chat"},{"id":"minimax-m2-7","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7","type":"chat"},{"id":"qwen3-6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.07,"output":0.42,"cache_read":0.035},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B","type":"chat"},{"id":"qwen3-5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.09,"output":0.13,"cache_read":0.045},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat"},{"id":"step-3-5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"canonical_model_id":"stepfun/step-3.5-flash-2603","display_name":"Step 3.5 Flash 2603","type":"chat"},{"id":"qwen3-5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.057,"output":0.459,"cache_read":0.057,"tiers":[{"input":0.229,"output":1.835,"cache_read":0.229,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat"},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.32,"output":3.96,"cache_read":1.32},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2-6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16000},"cost":{"input":0.8939,"output":3.7131,"cache_read":0.1788},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat"},{"id":"minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":524288},"cost":{"input":0.225,"output":0.9,"cache_read":0.045,"tiers":[{"input":0.45,"output":1.8,"cache_read":0.09,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.45,"output":1.8,"cache_read":0.09}},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5-3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat"},{"id":"fugu-ultra-v1-1","name":"Fugu Ultra v1.1","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra v1.1","type":"chat"},{"id":"kimi-k2-7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":1.9,"output":8,"cache_read":1.9},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat"},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.3,"output":1.2,"cache_read":0.3},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"qwen3-7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":256000}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.4,"tiers":[{"input":1.2,"output":4.8,"cache_read":1.2,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":1.2}},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat"},{"id":"glm-5-1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":38912}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202000,"output":128000},"cost":{"input":0.825,"output":3.301,"cache_read":0.165,"tiers":[{"input":1.1,"output":3.851,"cache_read":0.22,"tier":{"type":"context","size":32000}}]},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1","type":"chat"},{"id":"glm-4-6v-flash","name":"GLM 4.6V Flash","description":"Lightweight GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-4.6v-flash","display_name":"GLM 4.6V Flash","type":"chat"},{"id":"fugu-ultra-v2-0","name":"Fugu Ultra v2.0","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra v2.0","type":"chat"},{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.3,"output":1.2,"cache_read":0.3},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"mistral-small-4","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.15},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"qwen3-8-omni-flash","name":"Qwen3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":0.94,"cache_read":0.3},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","type":"chat"},{"id":"qwen3-5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.36,"output":2.21,"cache_read":0.36,"tiers":[{"input":1.08,"output":6.62,"cache_read":1.08,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.08,"output":6.62,"cache_read":1.08}},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat"},{"id":"muse-spark-1-3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":1},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.65,"output":3.3,"cache_read":1.65},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"qwen3-8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.16,"output":0.47,"cache_read":0.16},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat"},{"id":"gemma-3-27b","name":"Gemma 3 27B","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B","type":"chat"},{"id":"qwen3-6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":64000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.25,"tiers":[{"input":1,"output":4,"cache_read":1,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1,"output":4,"cache_read":1}},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat"},{"id":"seed-2-0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.4,"output":2.4,"cache_read":0.4,"tiers":[{"input":0.8,"output":4.8,"cache_read":0.8,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code","type":"chat"},{"id":"qwen3-8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.17,"output":0.5,"cache_read":0.08},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"muse-spark-1-1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":1},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat"},{"id":"step-3-7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":131072},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"qwen3-5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.172,"output":1.032,"cache_read":0.172,"tiers":[{"input":0.43,"output":2.58,"cache_read":0.43,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat"},{"id":"glm-4-5-flash","name":"GLM 4.5 Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":98304},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-4.5-flash","display_name":"GLM 4.5 Flash","type":"chat"},{"id":"gemma-4-26b-a4b","name":"Gemma 4 26B-A4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.29,"cache_read":0.025},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B-A4B","type":"chat"}]},"sensenova":{"id":"sensenova","api":"https://token.sensenova.cn/v1","name":"SenseNova (China)","doc":"https://platform.sensenova.cn/docs","display_name":"SenseNova (China)","models":[{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a high-performance conversational model by DeepSeek, supporting thinking/non-thinking modes, 1M context window, and tool calling.","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"sensenova-6.8-flash-lite","name":"SenseNova 6.8 Flash Lite","description":"SenseNova lightweight multimodal agent model for real-world complex tasks, data analysis, and complex information presentation","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"SenseNova 6.8 Flash Lite","type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"alibaba-token-plan":{"id":"alibaba-token-plan","api":"https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1","name":"Alibaba Token Plan","doc":"https://www.alibabacloud.com/help/en/model-studio/token-plan-overview","display_name":"Alibaba Token Plan","models":[{"id":"happyhorse-1.1-r2v","name":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"HappyHorse 1.1 Reference-to-Video","type":"chat"},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"happyhorse-1.1-t2v","name":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"HappyHorse 1.1 Text-to-Video","type":"chat"},{"id":"qwen-image-2.0","name":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen Image 2.0","type":"image-generation"},{"id":"glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-max-preview","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.8-max-preview","display_name":"Qwen3.8 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen-image-2.0-pro","name":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen Image 2.0 Pro","type":"image-generation"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"wan2.7-image","name":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Wan2.7 Image","type":"image-generation"},{"id":"wan2.7-image-pro","name":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Wan2.7 Image Pro","type":"image-generation"},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"happyhorse-1.1-i2v","name":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"HappyHorse 1.1 Image-to-Video","type":"chat"},{"id":"qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"input":196601,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-03","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0,"output":0},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"cloudflare-workers-ai":{"id":"cloudflare-workers-ai","api":"https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1","name":"Cloudflare Workers AI","doc":"https://developers.cloudflare.com/workers-ai/models/","display_name":"Cloudflare Workers AI","models":[{"id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","name":"Llama 3.3 70B Instruct fp8 Fast","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":24000,"output":24000},"cost":{"input":0.293,"output":2.253},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct fp8 Fast","type":"chat"},{"id":"@cf/meta/llama-guard-3-8b","name":"Llama Guard 3 8B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.484,"output":0.03},"canonical_model_id":"meta/llama-guard-3-8b","display_name":"Llama Guard 3 8B","type":"chat"},{"id":"@cf/meta/llama-3.1-8b-instruct-fp8","name":"Llama 3.1 8B Instruct fp8","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.152,"output":0.287},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama 3.1 8B Instruct fp8","type":"chat"},{"id":"@cf/meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.0485,"output":0.676},"canonical_model_id":"meta/llama-3.2-11b-vision-instruct","display_name":"Llama 3.2 11B Vision Instruct","type":"chat"},{"id":"@cf/meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":60000,"output":60000},"cost":{"input":0.027,"output":0.201},"canonical_model_id":"meta/llama-3.2-1b","display_name":"Llama 3.2 1B Instruct","type":"chat"},{"id":"@cf/meta/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":16384},"cost":{"input":0.27,"output":0.85},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B 16E Instruct","type":"chat"},{"id":"@cf/meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":80000,"output":80000},"cost":{"input":0.0509,"output":0.335},"canonical_model_id":"meta/llama-3.2-3b","display_name":"Llama 3.2 3B Instruct","type":"chat"},{"id":"@cf/google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","name":"Gemma Sea Lion V4 27B It","description":"Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"canonical_model_id":"aisingapore/gemma-sea-lion-v4-27b-it","display_name":"Gemma Sea Lion V4 27B It","type":"chat"},{"id":"@cf/ibm-granite/granite-4.0-h-micro","name":"Granite 4.0 H Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.017,"output":0.112},"canonical_model_id":"ibm/granite-4-h-micro","display_name":"Granite 4.0 H Micro","type":"chat"},{"id":"@cf/deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"@cf/deepseek-ai/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","name":"Deepseek R1 Distill Qwen 32B","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":80000,"output":80000},"cost":{"input":0.497,"output":4.881},"canonical_model_id":"deepseek/deepseek-r1","display_name":"Deepseek R1 Distill Qwen 32B","type":"chat"},{"id":"@cf/mistralai/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"canonical_model_id":"mistral/mistral-small-3-1-24b-instruct-2503","display_name":"Mistral Small 3.1 24B Instruct","type":"chat"},{"id":"@cf/moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"@cf/moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"@cf/zai-org/glm-5.3-flash","name":"Glm 5.3 Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"Glm 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"@cf/zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0605,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"@cf/zai-org/glm-5.2","name":"Glm 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"Glm 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"@cf/zai-org/glm-5.3","name":"Glm 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"Glm 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"@cf/nvidia/nemotron-3-120b-a12b","name":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"@cf/qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":3.2,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"@cf/qwen/qwq-32b","name":"Qwq 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":24000,"output":24000},"cost":{"input":0.66,"output":1},"canonical_model_id":"alibaba/qwq-32b","display_name":"Qwq 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"@cf/qwen/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3b fp8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.0509,"output":0.335},"canonical_model_id":"alibaba/qwen3-30b-a3b","display_name":"Qwen3 30B A3b fp8","type":"chat"},{"id":"@cf/qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.66,"output":1},"canonical_model_id":"alibaba/qwen2.5-coder-32b-instruct","display_name":"Qwen2.5 Coder 32B Instruct","type":"chat"},{"id":"@cf/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.2,"output":0.3},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"@cf/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.35,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"engy":{"id":"engy","api":"https://api.engy.ai/v1","name":"engy","doc":"https://engy.ai/pricing","display_name":"engy","models":[{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1001536,"input":936000,"output":65536},"cost":{"input":0.045,"output":0.32,"cache_read":0.015},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":327680,"input":294912,"output":32768},"cost":{"input":0.135,"output":0.45,"cache_read":0.027},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":920576,"output":128000},"cost":{"input":0.045,"output":0.09,"cache_read":0.009},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1113088,"input":1047552,"output":65536},"cost":{"input":1.95,"output":9.75,"cache_read":0.195},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":983040,"output":65536},"cost":{"input":0.04,"output":0.08,"cache_read":0.008},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":208192,"input":200000,"output":8192},"cost":{"input":0.045,"output":0.3,"cache_read":0.015},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":229376,"output":32768},"cost":{"input":0.68,"output":1.5,"cache_read":0.18},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":327680,"input":294912,"output":32768},"cost":{"input":0.98,"output":3.08,"cache_read":0.18},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":983040,"output":65536},"cost":{"input":0.04,"output":0.08,"cache_read":0.008},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"poolside":{"id":"poolside","api":"https://inference.poolside.ai/v1","name":"Poolside","doc":"https://platform.poolside.ai","display_name":"Poolside","models":[{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"poolside/laguna-xs-2.1","display_name":"Laguna XS 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"poolside/laguna-m.1","name":"Laguna M.1","description":"Poolside's open-weight model for agentic coding and long-horizon work","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"poolside/laguna-m.1","display_name":"Laguna M.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"nano-gpt":{"id":"nano-gpt","api":"https://nano-gpt.com/api/v1","name":"NanoGPT","doc":"https://docs.nano-gpt.com","display_name":"NanoGPT","models":[{"id":"deepseek-reasoner-cheaper","name":"Deepseek R1 Cheaper","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.4,"output":1.7,"cache_read":0.2},"display_name":"Deepseek R1 Cheaper","type":"chat"},{"id":"nano-gpt-help","name":"NanoGPT Help","description":"Text-only NanoGPT support assistant. Questions are processed by the Help inference provider; do not paste secrets or account credentials. Covers the website, models, API, pricing, memory, media generation, and support.","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-06-06","last_updated":"2026-06-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":6000,"input":6000,"output":512},"cost":{"input":0,"output":0},"display_name":"NanoGPT Help","type":"chat"},{"id":"doubao-seed-2-0-lite-260215","name":"Doubao Seed 2.0 Lite","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32000},"cost":{"input":0.1462,"output":0.8738,"cache_read":0.0731},"display_name":"Doubao Seed 2.0 Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-2-0-mini-260215","name":"Doubao Seed 2.0 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32000},"cost":{"input":0.0493,"output":0.4845,"cache_read":0.02465},"display_name":"Doubao Seed 2.0 Mini","type":"chat"},{"id":"fastgpt","name":"Web Answer","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-23","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":7.5,"output":7.5},"display_name":"Web Answer","type":"chat"},{"id":"doubao-seed-2-0-pro-260215","name":"Doubao Seed 2.0 Pro","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":0.782,"output":3.876,"cache_read":0.391},"display_name":"Doubao Seed 2.0 Pro","type":"chat"},{"id":"ernie-5.0-thinking-preview","name":"Ernie 5.0 Thinking Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":1,"output":3.5,"cache_read":0.5},"display_name":"Ernie 5.0 Thinking Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-flash-lite-preview-09-2025-thinking","name":"Gemini 2.5 Flash Lite Preview (09/2025) – Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"display_name":"Gemini 2.5 Flash Lite Preview (09/2025) – Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemma-4-12b-it-station-keeper","name":"Gemma 4 12B StationKeeper","description":"Gemma 4 12B StationKeeper is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 131,072-token context window.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-09","last_updated":"2026-09-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.05,"output":0.25,"cache_read":0.025},"display_name":"Gemma 4 12B StationKeeper","type":"chat"},{"id":"glm-4-air-0111","name":"GLM 4 Air 0111","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-01-11","last_updated":"2025-01-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":0.1394,"output":0.1394,"cache_read":0.0697},"display_name":"GLM 4 Air 0111","type":"chat"},{"id":"glm-4.1v-thinking-flashx","name":"GLM 4.1V Thinking FlashX","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm-flash","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":64000,"input":64000,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"display_name":"GLM 4.1V Thinking FlashX","type":"chat"},{"id":"deepseek-v3-0324","name":"DeepSeek Chat 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2,"output":0.77,"cache_read":0.135},"canonical_model_id":"deepseek/deepseek-v3-0324","display_name":"DeepSeek Chat 0324","type":"chat"},{"id":"venice-uncensored","name":"Venice Uncensored","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"venice","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-10-01","last_updated":"2025-02-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.4,"output":1.8,"cache_read":0.4},"display_name":"Venice Uncensored","type":"chat"},{"id":"Gemma-4-31B-MeroMero-v2:thinking","name":"Gemma 4 31B MeroMero v2 Thinking","description":"Gemma 4 31B MeroMero v2 with thinking enabled for more deliberate emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-08-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Gemma 4 31B MeroMero v2 Thinking","type":"chat"},{"id":"gemini-2.0-pro-reasoner","name":"Gemini 2.0 Pro Reasoner","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-02-05","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":1.292,"output":4.998,"cache_read":0.323},"display_name":"Gemini 2.0 Pro Reasoner","type":"chat"},{"id":"Meta-Llama-3-1-8B-Instruct-FP8","name":"Llama 3.1 8B (decentralized)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.02,"output":0.03,"cache_read":0.01},"display_name":"Llama 3.1 8B (decentralized)","type":"chat"},{"id":"glm-4-plus-0111","name":"GLM 4 Plus 0111","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":9.996,"output":9.996,"cache_read":4.998},"display_name":"GLM 4 Plus 0111","type":"chat"},{"id":"holo3-35b-a3b:thinking","name":"Holo3-35B-A3B Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.25,"output":1.8,"cache_read":0.125},"display_name":"Holo3-35B-A3B Thinking","type":"chat"},{"id":"gemma-4-26b-a4b-it-moonlight","name":"Moonlight Dusk","description":"Moonlight Dusk is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Moonlight Dusk","type":"chat"},{"id":"phi-4-mini-instruct","name":"Phi 4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.17,"output":0.68,"cache_read":0.085},"display_name":"Phi 4 Mini","type":"chat"},{"id":"auto-model-premium","name":"Auto model (Premium)","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":9.996,"output":19.992,"cache_read":4.998},"display_name":"Auto model (Premium)","type":"chat"},{"id":"gemma-4-31b-it-darkidol","name":"DarkIdol","description":"DarkIdol is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"DarkIdol","type":"chat"},{"id":"gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Gemini 2.5 Flash Lite Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-preview-09-2025","name":"Gemini 2.5 Flash Preview (09/2025)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"display_name":"Gemini 2.5 Flash Preview (09/2025)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemma-4-26b-a4b-it-opusdistill","name":"Opus Distill","description":"Opus Distill is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Opus Distill","type":"chat"},{"id":"auto-model-standard","name":"Auto model (Standard)","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":9.996,"output":19.992,"cache_read":4.998},"display_name":"Auto model (Standard)","type":"chat"},{"id":"longcat-2.0","name":"LongCat 2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.75,"output":3,"cache_read":0.015},"canonical_model_id":"meituan/longcat-2.0","display_name":"LongCat 2.0","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-pro-preview-03-25","name":"Gemini 2.5 Pro Preview 0325","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"display_name":"Gemini 2.5 Pro Preview 0325","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"agnes-3.0-flash","name":"Agnes 3.0 Flash","description":"Agnes 3.0 Flash is a low-cost model for coding, tool use, and multi-turn agent tasks. It supports text and image input, optional thinking, and a 512K-token context window.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-09","last_updated":"2026-09-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":65536},"cost":{"input":0.05,"output":0.15,"cache_read":0.005},"display_name":"Agnes 3.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Gemma-4-31B-Queen","name":"Gemma 4 31B Queen","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"display_name":"Gemma 4 31B Queen","type":"chat"},{"id":"auto-model","name":"Auto model","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":0,"output":0},"display_name":"Auto model","type":"chat"},{"id":"qvq-max","name":"Qwen: QvQ Max","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-03-28","last_updated":"2025-03-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":1.2,"output":4.8,"cache_read":0.6},"display_name":"Qwen: QvQ Max","type":"chat"},{"id":"asi1-mini","name":"ASI1 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":1,"output":1,"cache_read":0.5},"display_name":"ASI1 Mini","type":"chat"},{"id":"gemini-2.5-pro-exp-03-25","name":"Gemini 2.5 Pro Experimental 0325","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"display_name":"Gemini 2.5 Pro Experimental 0325","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemma-4-31b-it-isometry","name":"Isometry","description":"Isometry is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Isometry","type":"chat"},{"id":"celeris-1","name":"Celeris 1","description":"Celeris 1 is a diffusion language model built for ultra-low-latency classification, extraction, judging, query rewriting, and other short structured responses.","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-07-25","last_updated":"2026-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":2,"output":6,"cache_read":1},"display_name":"Celeris 1","type":"chat"},{"id":"gemini-3-pro-image-preview","name":"Gemini 3 Pro Image","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"input":65536,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2},"canonical_model_id":"google/gemini-3-pro-image-preview","display_name":"Gemini 3 Pro Image","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemma-4-26b-a4b-it-darksoul","name":"Dark Soul","description":"Dark Soul is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Dark Soul","type":"chat"},{"id":"glm-4.1v-thinking-flash","name":"GLM 4.1V Thinking Flash","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm-flash","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":64000,"input":64000,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"display_name":"GLM 4.1V Thinking Flash","type":"chat"},{"id":"Gemma-4-31B-GarnetV2","name":"Gemma 4 31B Garnet V2","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"display_name":"Gemma 4 31B Garnet V2","type":"chat"},{"id":"gemini-2.5-flash-nothinking","name":"Gemini 2.5 Flash (No Thinking)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"structured_output":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"display_name":"Gemini 2.5 Flash (No Thinking)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"Gemma-4-31B-MeroMero-v2","name":"Gemma 4 31B MeroMero v2","description":"Gemma 4 31B MeroMero v2 is a LoRA finetune for emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-08-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Gemma 4 31B MeroMero v2","type":"chat"},{"id":"holo3-35b-a3b","name":"Holo3-35B-A3B","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.25,"output":1.8,"cache_read":0.125},"display_name":"Holo3-35B-A3B","type":"chat"},{"id":"claw-medium","name":"Claw Medium","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"display_name":"Claw Medium","type":"chat"},{"id":"gemma-4-26b-a4b-it-shadowsiren","name":"Shadow Siren","description":"Shadow Siren is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Shadow Siren","type":"chat"},{"id":"gemini-2.0-pro-exp-02-05","name":"Gemini 2.0 Pro 0205","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-02-05","last_updated":"2025-02-05","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":2097152,"input":2097152,"output":8192},"cost":{"input":1.989,"output":7.956,"cache_read":0.49725},"display_name":"Gemini 2.0 Pro 0205","type":"chat"},{"id":"claw-high","name":"Claw High","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"display_name":"Claw High","type":"chat"},{"id":"deepseek-chat","name":"DeepSeek V3/Deepseek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.1,"output":0.425,"cache_read":0.05},"canonical_model_id":"deepseek/deepseek-chat","display_name":"DeepSeek V3/Deepseek Chat","type":"chat"},{"id":"Gemma-4-26B-A4B-MeroMero:thinking","name":"Gemma 4 26B A4B MeroMero Thinking","description":"Gemma 4 26B A4B MeroMero with thinking enabled for more deliberate emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Gemma 4 26B A4B MeroMero Thinking","type":"chat"},{"id":"claw-low","name":"Claw Low","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0.08333},"display_name":"Claw Low","type":"chat"},{"id":"doubao-1.5-pro-32k","name":"Doubao 1.5 Pro 32k","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-11-20","last_updated":"2025-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.1343,"output":0.3349,"cache_read":0.06715},"display_name":"Doubao 1.5 Pro 32k","type":"chat"},{"id":"doubao-seed-2-0-code-preview-260215","name":"Doubao Seed 2.0 Code Preview","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":0.782,"output":3.893,"cache_read":0.391},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Doubao Seed 2.0 Code Preview","type":"chat"},{"id":"hermes-low","name":"Hermes Low","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0.08333},"display_name":"Hermes Low","type":"chat"},{"id":"gemma-4-31b-it-gemsicle","name":"Gemsicle","description":"Gemsicle is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Gemsicle","type":"chat"},{"id":"mercury-coder-small","name":"Mercury Coder Small","description":"Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.","family":"mercury","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.25,"output":1,"cache_read":0.125},"display_name":"Mercury Coder Small","type":"chat"},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"hermes-high","name":"Hermes High","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"display_name":"Hermes High","type":"chat"},{"id":"gemini-2.5-flash-preview-05-20","name":"Gemini 2.5 Flash 0520","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"structured_output":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"input":1048000,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Gemini 2.5 Flash 0520","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-4-long","name":"GLM-4 Long","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":4095},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"display_name":"GLM-4 Long","type":"chat"},{"id":"pokee-isaac","name":"Pokee-Isaac 28B","description":"Pokee-Isaac is a 28B agentic model with a roughly 10-million-token context window, function calling, and OpenAI-compatible structured output. Pokee bills in $0.01 increments, rounding each non-zero request up to the next cent.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-04","last_updated":"2026-08-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":10000000,"input":10000000,"output":60000},"cost":{"input":0.15,"output":1,"cache_read":0.075},"display_name":"Pokee-Isaac 28B","type":"chat"},{"id":"MiniMax-M1","name":"MiniMax M1","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"minimax","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-01-08","last_updated":"2025-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.1394,"output":1.3328,"cache_read":0.0697},"display_name":"MiniMax M1","type":"chat"},{"id":"Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled","name":"Gemma 4 31B Claude 4.6 Opus Reasoning Distilled","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"claude","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.0306},"display_name":"Gemma 4 31B Claude 4.6 Opus Reasoning Distilled","type":"chat"},{"id":"Qwen3.5-27B-BlueStar-v3-Derestricted","name":"Qwen3.5 27B BlueStar v3 Derestricted","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"display_name":"Qwen3.5 27B BlueStar v3 Derestricted","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemma-4-31b-it-novelist","name":"Novelist","description":"Novelist is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Novelist","type":"chat"},{"id":"ernie-5.1:thinking","name":"ERNIE 5.1 Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2026-05-10","last_updated":"2026-05-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":119000,"input":119000,"output":64000},"cost":{"input":0.75,"output":3,"cache_read":0.75},"display_name":"ERNIE 5.1 Thinking","type":"chat"},{"id":"gemma-4-12b-it-semancer","name":"Gemma 4 12B Semancer","description":"Gemma 4 12B Semancer is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 131,072-token context window.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-09","last_updated":"2026-09-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.05,"output":0.25,"cache_read":0.025},"display_name":"Gemma 4 12B Semancer","type":"chat"},{"id":"mistral-code-latest","name":"Mistral Code Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.15},"display_name":"Mistral Code Latest","type":"chat"},{"id":"Qwen3.5-27B-Queen-Derestricted","name":"Qwen3.5 27B Queen Derestricted","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"display_name":"Qwen3.5 27B Queen Derestricted","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemma-4-31b-it-fabled","name":"Fabled","description":"Fabled is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Fabled","type":"chat"},{"id":"gemma-4-26b-a4b-it-chimeraxheretic","name":"Gemma 4 26B A4B Chimera X Heretic","description":"Chimera X Heretic is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-08","last_updated":"2026-10-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Gemma 4 26B A4B Chimera X Heretic","type":"chat"},{"id":"Gemma-4-26B-A4B-MeroMero","name":"Gemma 4 26B A4B MeroMero","description":"Gemma 4 26B A4B MeroMero is an NVFP4 multimodal mixture-of-experts fine-tune for emotive dialogue, relationship scenes, creative writing, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Gemma 4 26B A4B MeroMero","type":"chat"},{"id":"Gemma-4-31B-Cognitive-Unshackled","name":"Gemma 4 31B Cognitive Unshackled","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"display_name":"Gemma 4 31B Cognitive Unshackled","type":"chat"},{"id":"universal-summarizer","name":"Universal Summarizer","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-23","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":30,"output":30},"display_name":"Universal Summarizer","type":"chat"},{"id":"gemma-4-12b-it","name":"Gemma 4 12B Instruct","description":"Compact Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.05,"output":0.25,"cache_read":0.025},"canonical_model_id":"google/gemma-4-12b-it","display_name":"Gemma 4 12B Instruct","type":"chat"},{"id":"gemini-exp-1206","name":"Gemini 2.0 Pro 1206","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":2097152,"input":2097152,"output":8192},"cost":{"input":1.258,"output":4.998,"cache_read":0.629},"display_name":"Gemini 2.0 Pro 1206","type":"chat"},{"id":"gemini-2.5-flash-preview-09-2025-thinking","name":"Gemini 2.5 Flash Preview (09/2025) – Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"display_name":"Gemini 2.5 Flash Preview (09/2025) – Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"doubao-1.5-pro-256k","name":"Doubao 1.5 Pro 256k","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":16384},"cost":{"input":0.799,"output":1.445,"cache_read":0.3995},"display_name":"Doubao 1.5 Pro 256k","type":"chat"},{"id":"gemma-4-31b-it-garnet","name":"Garnet","description":"Garnet is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Garnet","type":"chat"},{"id":"gemini-2.5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 0506","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-05-06","last_updated":"2025-05-06","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"display_name":"Gemini 2.5 Pro Preview 0506","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"canonical_model_id":"inception/mercury-2","display_name":"Mercury 2","type":"chat"},{"id":"command-a-reasoning-08-2025","name":"Cohere Command A (08/2025)","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":8192},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"cohere/command-a-reasoning-08-2025","display_name":"Cohere Command A (08/2025)","type":"chat"},{"id":"longcat-2.0:thinking","name":"LongCat 2.0 Thinking","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.75,"output":3,"cache_read":0.015},"canonical_model_id":"meituan/longcat-2.0","display_name":"LongCat 2.0 Thinking","type":"chat"},{"id":"deepseek-r1-sambanova","name":"DeepSeek R1 Fast","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":4.998,"output":6.987,"cache_read":2.499},"display_name":"DeepSeek R1 Fast","type":"chat"},{"id":"gemini-2.5-flash-preview-04-17","name":"Gemini 2.5 Flash Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-04-17","last_updated":"2025-04-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Gemini 2.5 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"input":64000,"output":65536},"cost":{"input":0.4,"output":1.7,"cache_read":0.2},"canonical_model_id":"deepseek/deepseek-reasoner","display_name":"DeepSeek Reasoner","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.5-flash-lite-preview-09-2025","name":"Gemini 2.5 Flash Lite Preview (09/2025)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"display_name":"Gemini 2.5 Flash Lite Preview (09/2025)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-preview-04-17:thinking","name":"Gemini 2.5 Flash Preview Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-04-17","last_updated":"2025-04-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.15,"output":3.5,"cache_read":0.015},"display_name":"Gemini 2.5 Flash Preview Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"deepseek-r1","name":"DeepSeek R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.4,"output":1.7,"cache_read":0.2},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.5-pro-preview-06-05","name":"Gemini 2.5 Pro Preview 0605","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"display_name":"Gemini 2.5 Pro Preview 0605","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"deepseek-chat-cheaper","name":"DeepSeek V3/Chat Cheaper","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"deepseek","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.1,"output":0.425,"cache_read":0.05},"display_name":"DeepSeek V3/Chat Cheaper","type":"chat"},{"id":"gemma-4-31b-it-scarlet","name":"Gemma 4 31B Scarlet","description":"Scarlet is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-08","last_updated":"2026-10-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Gemma 4 31B Scarlet","type":"chat"},{"id":"GLM-4.6-Derestricted-v5","name":"GLM 4.6 Derestricted v5","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.4,"output":1.5,"cache_read":0.2},"display_name":"GLM 4.6 Derestricted v5","type":"chat"},{"id":"longcat-2.5-preview","name":"LongCat 2.5 Preview","description":"Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window","family":"longcat","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-25","last_updated":"2026-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.75,"output":2.95,"cache_read":0.015},"canonical_model_id":"meituan/longcat-2.5-preview","display_name":"LongCat 2.5 Preview","type":"chat"},{"id":"doubao-1.5-vision-pro-32k","name":"Doubao 1.5 Vision Pro 32k","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-11-20","last_updated":"2025-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.459,"output":1.377,"cache_read":0.2295},"display_name":"Doubao 1.5 Vision Pro 32k","type":"chat"},{"id":"glm-z1-airx","name":"GLM Z1 AirX","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":16384},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"display_name":"GLM Z1 AirX","type":"chat"},{"id":"auto-model-basic","name":"Auto model (Basic)","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":9.996,"output":19.992,"cache_read":4.998},"display_name":"Auto model (Basic)","type":"chat"},{"id":"qwen3-vl-235b-a22b-instruct-original","name":"Qwen3 VL 235B A22B Instruct Original","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.3,"output":1.9,"cache_read":0.15},"display_name":"Qwen3 VL 235B A22B Instruct Original","type":"chat"},{"id":"gemma-4-26b-a4b-it-luminous","name":"Luminous Mirror","description":"Luminous Mirror is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Luminous Mirror","type":"chat"},{"id":"sarvam-105b","name":"Sarvam 105B","description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":4096},"cost":{"input":0.054,"output":0.2124,"cache_read":0.0336},"canonical_model_id":"sarvam/sarvam-105b","display_name":"Sarvam 105B","type":"chat"},{"id":"gemma-4-31b-it-gembrain","name":"Gembrain","description":"Gembrain is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Gembrain","type":"chat"},{"id":"phi-4-multimodal-instruct","name":"Phi 4 Multimodal","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.07,"output":0.11,"cache_read":0.035},"display_name":"Phi 4 Multimodal","type":"chat"},{"id":"gemini-2.5-flash-preview-05-20:thinking","name":"Gemini 2.5 Flash 0520 Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"input":1048000,"output":65536},"cost":{"input":0.15,"output":3.5,"cache_read":0.015},"display_name":"Gemini 2.5 Flash 0520 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemma-4-26b-a4b-it-musica","name":"Musica","description":"Musica is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Musica","type":"chat"},{"id":"gemma-4-26b-a4b-it-chimerax","name":"Chimera X","description":"Chimera X is a Gemma 4 26B A4B multimodal mixture-of-experts fine-tune for creative writing, expressive dialogue, and roleplay.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.12,"output":0.38,"cache_read":0.06},"display_name":"Chimera X","type":"chat"},{"id":"hermes-medium","name":"Hermes Medium","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"display_name":"Hermes Medium","type":"chat"},{"id":"Gemma-4-31B-DarkIdol","name":"Gemma 4 31B DarkIdol","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"display_name":"Gemma 4 31B DarkIdol","type":"chat"},{"id":"ernie-5.1","name":"ERNIE 5.1","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"release_date":"2026-05-10","last_updated":"2026-05-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":119000,"input":119000,"output":64000},"cost":{"input":0.75,"output":3,"cache_read":0.75},"display_name":"ERNIE 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-code-agent-latest","name":"Mistral Code Agent Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.4,"output":2,"cache_read":0.2},"display_name":"Mistral Code Agent Latest","type":"chat"},{"id":"kimi-k2-instruct-fast","name":"Kimi K2 0711 Fast","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"kimi-k2","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-15","last_updated":"2025-07-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"display_name":"Kimi K2 0711 Fast","type":"chat"},{"id":"featherless-ai/Qwerky-72B","name":"Qwerky 72B","description":"General-purpose chat model for instruction following, writing, and analysis","family":"qwerky","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"display_name":"Qwerky 72B","type":"chat"},{"id":"reka/reka-edge-2603","name":"Reka Edge 2603","description":"Reka's compact multimodal model for visual understanding and tool use, served directly by Reka.","family":"reka","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.105,"output":0.105},"display_name":"Reka Edge 2603","type":"chat"},{"id":"reka/reka-flash-3","name":"Reka Flash 3","description":"Reka's 21B reasoning model for chat and coding, served directly by Reka.","family":"reka","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":65536},"cost":{"input":0.105,"output":0.21},"display_name":"Reka Flash 3","type":"chat"},{"id":"unsloth/gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"unsloth","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":96000},"cost":{"input":0.2992,"output":0.2992,"cache_read":0.1496},"display_name":"Gemma 3 27B IT","type":"chat"},{"id":"unsloth/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"unsloth","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.272,"output":0.272,"cache_read":0.136},"display_name":"Gemma 3 12B IT","type":"chat"},{"id":"unsloth/gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"unsloth","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"display_name":"Gemma 3 4B IT","type":"chat"},{"id":"bytedance-seed/seed-2.0-lite","name":"ByteDance Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.25,"output":2,"cache_read":0.125},"canonical_model_id":"bytedance-seed/seed-2.0-lite","display_name":"ByteDance Seed 2.0 Lite","type":"chat"},{"id":"bytedance-seed/seed-2-1-turbo","name":"ByteDance Seed 2.1 Turbo","description":"ByteDance Seed 2.1 Turbo is a multimodal model for coding and long-horizon agent workflows, including end-to-end software delivery and multi-step task execution. It supports text, image, and video input with a 262k context window.","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":235929},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"display_name":"ByteDance Seed 2.1 Turbo","type":"chat"},{"id":"bytedance-seed/seed-2.0-code","name":"ByteDance Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.25},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"ByteDance Seed 2.0 Code","type":"chat"},{"id":"poolside/laguna-s-2.1:thinking","name":"Laguna S 2.1 Thinking","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1 Thinking","type":"chat"},{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"abliteration-ai/abliterated-model-large-v2","name":"Abliterated Model Large V2","description":"Abliteration.ai's default large text reasoning model is derived from GLM-5.3 for harder reasoning and evaluation workloads, with automatic prompt caching and a one-million-token context window.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-31","last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":999990},"cost":{"input":3,"output":5,"cache_read":0.3},"display_name":"Abliterated Model Large V2","type":"chat"},{"id":"abliteration-ai/abliterated-model","name":"Abliterated Model","description":"Abliteration.ai's multimodal reasoning model supports text and image input, structured output, automatic prompt caching, and a 262K-token context window.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":262134},"cost":{"input":1,"output":3,"cache_read":0.1},"display_name":"Abliterated Model","type":"chat"},{"id":"abliteration-ai/abliterated-model-large","name":"Abliterated Model Large","description":"Abliteration.ai's large text reasoning model is derived from GLM-5.2 and supports native tool calling, structured output, automatic prompt caching, and a one-million-token context window.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":999990},"cost":{"input":3,"output":5,"cache_read":0.3},"display_name":"Abliterated Model Large","type":"chat"},{"id":"prism-ml/ternary-bonsai-2-27b","name":"Ternary Bonsai 2 27B","description":"Ternary Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.075,"output":0.5,"cache_read":0.0375},"display_name":"Ternary Bonsai 2 27B","type":"chat"},{"id":"anthropic/claude-opus-4.5:thinking","name":"Claude 4.5 Opus Thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude 4.5 Opus Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-sonnet-4.5:thinking","name":"Claude Sonnet 4.5 Thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.6:thinking:low","name":"Claude 4.6 Opus Thinking Low","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude 4.6 Opus Thinking Low","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.1","name":"Claude 4.1 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude 4.1 Opus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.5","name":"Claude 4.5 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude 4.5 Opus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Claude 4.6 Opus","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude 4.6 Opus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude 4.7 Opus","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude 4.7 Opus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-opus-latest","name":"Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"display_name":"Claude Opus Latest","type":"chat"},{"id":"anthropic/claude-opus-4.1:thinking:1024","name":"Claude 4.1 Opus Thinking (1K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude 4.1 Opus Thinking (1K)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-haiku-latest","name":"Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"display_name":"Claude Haiku Latest","type":"chat"},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-5.5:thinking","name":"Claude Sonnet 5.5 Thinking","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true}}},{"id":"anthropic/claude-opus-4.6:thinking","name":"Claude 4.6 Opus Thinking","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude 4.6 Opus Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-latest","name":"Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"display_name":"Claude Sonnet Latest","type":"chat"},{"id":"anthropic/claude-opus-4.6:thinking:medium","name":"Claude 4.6 Opus Thinking Medium","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude 4.6 Opus Thinking Medium","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-fable-latest","name":"Claude Fable Latest","description":"Compatibility alias for Claude Fable.","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"display_name":"Claude Fable Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.1:thinking:8192","name":"Claude 4.1 Opus Thinking (8K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude 4.1 Opus Thinking (8K)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-haiku-4.5:thinking","name":"Claude Haiku 4.5 Thinking","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4.8:thinking","name":"Claude Opus 4.8 Thinking","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.6:thinking","name":"Claude Sonnet 4.6 Thinking","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.6:thinking:max","name":"Claude 4.6 Opus Thinking Max","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude 4.6 Opus Thinking Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-5:thinking","name":"Claude Sonnet 5 Thinking","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7:thinking","name":"Claude 4.7 Opus Thinking","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude 4.7 Opus Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"anthropic/claude-opus-4.1:thinking","name":"Claude 4.1 Opus Thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude 4.1 Opus Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.1:thinking:32768","name":"Claude 4.1 Opus Thinking (32K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude 4.1 Opus Thinking (32K)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":2.856,"output":14.246,"cache_read":1.428},"canonical_model_id":"cohere/command-r-plus-08-2024","display_name":"Cohere: Command R+","type":"chat"},{"id":"deepseek/deepseek-v4-flash:thinking","name":"DeepSeek V4 Flash (Thinking)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Thinking)","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.05,"output":0.16,"cache_read":0.013},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-0423","name":"DeepSeek V4 Flash 0423","description":"Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0423","display_name":"DeepSeek V4 Flash 0423","type":"chat"},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":0.09,"output":0.3,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash:thinking","name":"DeepSeek V4.1 Flash Thinking","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":0.09,"output":0.3,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash Thinking","type":"chat"},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.2156,"output":0.6468,"cache_read":0.00686},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v3.2:thinking","name":"DeepSeek V3.2 Thinking","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":163000,"input":163000,"output":65536},"cost":{"input":0.2088,"output":0.3096,"cache_read":0.0216},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2 Thinking","type":"chat"},{"id":"deepseek/deepseek-v4.1-flash-1017:thinking","name":"DeepSeek V4.1 Flash 1017 Thinking","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":393216},"cost":{"input":0.1,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017 Thinking","type":"chat"},{"id":"deepseek/deepseek-latest","name":"DeepSeek Latest","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.13332,"output":0.39996,"cache_read":0.004242},"display_name":"DeepSeek Latest","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0423:thinking","name":"DeepSeek V4 Flash 0423 (Thinking)","description":"Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0423","display_name":"DeepSeek V4 Flash 0423 (Thinking)","type":"chat"},{"id":"deepseek/deepseek-v4-pro:thinking","name":"DeepSeek V4 Pro (Thinking)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.7,"output":1.4,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (Thinking)","type":"chat"},{"id":"deepseek/deepseek-v4-pro-0813:thinking","name":"DeepSeek V4 Pro 0813 Thinking","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.13332,"output":0.39996,"cache_read":0.004242},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 Thinking","type":"chat"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.13332,"output":0.39996,"cache_read":0.004242},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-0731:thinking","name":"DeepSeek V4 Flash 0731 (Thinking)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.05,"output":0.16,"cache_read":0.013},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Thinking)","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.7,"output":1.4,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","description":"Compatibility alias that routes to the newest dated DeepSeek V4 Flash release. Currently routes to DeepSeek V4 Flash 0731. ⚠️ This route goes directly to DeepSeek, so privacy and logging guarantees are limited.","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":393216},"cost":{"input":0.1,"output":0.6,"cache_read":0.003},"display_name":"DeepSeek V4 Flash Latest","type":"chat"},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":163000,"input":163000,"output":65536},"cost":{"input":0.2088,"output":0.3096,"cache_read":0.0216},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":393216},"cost":{"input":0.1,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"baseten/Kimi-K2-Instruct-FP4","name":"Kimi K2 0711 Instruct FP4","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":131072},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"display_name":"Kimi K2 0711 Instruct FP4","type":"chat"},{"id":"unbiased/pareto-26.9","name":"Pareto 26.9","description":"Pareto 26.9 is an experimental multimodal composite model from Unbiased AI for research, coding, agentic workflows, and general-purpose tasks. It runs several frontier and open models for each request and returns a single selected or synthesized answer. This experimental release supports text and image input, tool calling, a 262K-token context window, and up to 131K output tokens. Its underlying model mix and behavior may change as it is evaluated. Request content may be retained for abuse prevention and security monitoring for up to 30 days, and is not used for model training without explicit consent.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":2.5,"output":7.5,"cache_read":0.25},"display_name":"Pareto 26.9","type":"chat"},{"id":"unbiased/pareto-26.10","name":"Pareto 26.10","description":"Pareto 26.10 is Unbiased AI's multimodal composite model for research, coding, and agentic workflows. It accepts text and images, supports tool calling, and provides a 1M-token context window with up to 131K output tokens. This is the stable release of Pareto 26.10. Tool selection is automatic; forced tool selection, structured output, and adjustable reasoning controls are not supported.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.8,"output":3.2,"cache_read":0.03},"display_name":"Pareto 26.10","type":"chat"},{"id":"lightonai/LightOnOCR-2-1B","name":"LightOnOCR 2","description":"LightOnOCR 2 hosted by IONOS in Berlin, Germany. Zero data retention.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.1785,"output":0.3465},"display_name":"LightOnOCR 2","type":"chat"},{"id":"abacusai/Dracarys-72B-Instruct","name":"Llama 3.1 70B Dracarys 2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-08-02","last_updated":"2025-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Llama 3.1 70B Dracarys 2","type":"chat"},{"id":"shisa-ai/shisa-v2.1-llama3.3-70b","name":"Shisa V2.1 Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":4096},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"display_name":"Shisa V2.1 Llama 3.3 70B","type":"chat"},{"id":"shisa-ai/shisa-v2-llama3.3-70b","name":"Shisa V2 Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"display_name":"Shisa V2 Llama 3.3 70B","type":"chat"},{"id":"Steelskull/L3.3-MS-Nevoria-70b","name":"Steelskull Nevoria 70b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Steelskull Nevoria 70b","type":"chat"},{"id":"Steelskull/L3.3-Cu-Mai-R1-70b","name":"Llama 3.3 70B Cu Mai","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Llama 3.3 70B Cu Mai","type":"chat"},{"id":"Steelskull/L3.3-Nevoria-R1-70b","name":"Steelskull Nevoria R1 70b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Steelskull Nevoria R1 70b","type":"chat"},{"id":"Steelskull/L3.3-Electra-R1-70b","name":"Steelskull Electra R1 70b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.69989,"output":0.69989,"cache_read":0.349945},"display_name":"Steelskull Electra R1 70b","type":"chat"},{"id":"tencent/hy3","name":"Tencent Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":128000},"cost":{"input":0.066,"output":0.26,"cache_read":0.029},"canonical_model_id":"tencent/hy3","display_name":"Tencent Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy4-preview","name":"Tencent Hy4 Preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":64000},"cost":{"input":0.7506,"output":2.2509,"cache_read":0.0378},"canonical_model_id":"tencent/hy4-preview","display_name":"Tencent Hy4 Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":2.006,"output":2.992,"cache_read":1.003},"canonical_model_id":"anthracite-org/magnum-v4-72b","display_name":"Magnum v4 72B","type":"chat"},{"id":"anthracite-org/magnum-v2-72b","name":"Magnum V2 72B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":2.006,"output":2.992,"cache_read":1.003},"display_name":"Magnum V2 72B","type":"chat"},{"id":"meta-llama/llama-4-scout","name":"Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":328000,"input":328000,"output":65536},"cost":{"input":0.085,"output":0.46,"cache_read":0.0425},"display_name":"Llama 4 Scout","type":"chat"},{"id":"meta-llama/llama-4-maverick","name":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.1875,"output":0.6525,"cache_read":0.05},"display_name":"Llama 4 Maverick","type":"chat"},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama 3.3 70b Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.05,"output":0.23,"cache_read":0.025},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70b Instruct","type":"chat"},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama 3.1 8b Instruct","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.02,"output":0.04,"cache_read":0.0272},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama 3.1 8b Instruct","type":"chat"},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Llama 3.2 3b Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-09-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.0306,"output":0.0493,"cache_read":0.0153},"display_name":"Llama 3.2 3b Instruct","type":"chat"},{"id":"LLM360/K2-Think","name":"K2-Think","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":0.17,"output":0.68,"cache_read":0.085},"display_name":"K2-Think","type":"chat"},{"id":"deepcogito/cogito-v1-preview-qwen-32B","name":"Cogito v1 Preview Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-05-10","last_updated":"2025-05-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":1.8,"output":1.8,"cache_read":0.9},"display_name":"Cogito v1 Preview Qwen 32B","type":"chat"},{"id":"GalrionSoftworks/MN-LooseCannon-12B-v1","name":"MN-LooseCannon-12B-v1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"MN-LooseCannon-12B-v1","type":"chat"},{"id":"meganova-ai/manta-mini-1.0","name":"Manta Mini 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-20","last_updated":"2025-12-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":0.02,"output":0.16,"cache_read":0.01},"display_name":"Manta Mini 1.0","type":"chat"},{"id":"meganova-ai/manta-flash-1.0","name":"Manta Flash 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-20","last_updated":"2025-12-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.02,"output":0.16,"cache_read":0.01},"display_name":"Manta Flash 1.0","type":"chat"},{"id":"meganova-ai/manta-pro-1.0","name":"Manta Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-20","last_updated":"2025-12-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"input":65536,"output":32768},"cost":{"input":0.06,"output":0.5,"cache_read":0.03},"display_name":"Manta Pro 1.0","type":"chat"},{"id":"perceptron/perceptron-mk1","name":"Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.15,"output":1.5,"cache_read":0.075},"canonical_model_id":"perceptron/perceptron-mk1","display_name":"Perceptron Mk1","type":"chat"},{"id":"perceptron/perceptron-mk1.5","name":"Perceptron Mk1.5","description":"Perceptron Mk1.5 is a multimodal reasoning model for visual analysis and physical agents. It accepts text, images, video, and audio, supports tool calling and structured output, and can return spatial annotations such as points, boxes, polygons, and tracks.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-25","last_updated":"2026-09-25","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":36864,"input":36864,"output":8192},"cost":{"input":0.15,"output":1.5},"display_name":"Perceptron Mk1.5","type":"chat"},{"id":"z-ai/glm-4.6v","name":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":24000},"cost":{"input":0.3,"output":0.9,"cache_read":0.15},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM 4.6V","type":"chat"},{"id":"z-ai/glm-4.6-original","name":"GLM 4.6 Original","description":"GLM-4.6, Zhipu's flagship text model with 256K context window and advanced reasoning capabilities. Direct via Z-AI (Zhipu).","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65535},"cost":{"input":0.5,"output":2,"cache_read":0.1},"display_name":"GLM 4.6 Original","type":"chat"},{"id":"z-ai/glm-4.5","name":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.3,"output":1.3,"cache_read":0.15},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM 4.5","type":"chat"},{"id":"z-ai/glm-5.3-flash-apex-abliterated","name":"Apex Flash 1 Abliterated","description":"Apex Flash 1 Abliterated is an experimental derivative of Cantina Security and Yeta's Apex Flash 1 with modified refusal behavior.","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":32768},"cost":{"input":0.15,"output":0.5,"cache_read":0.075},"display_name":"Apex Flash 1 Abliterated","type":"chat"},{"id":"z-ai/glm-5v-turbo","name":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"input":202800,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM 5V Turbo","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.025},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flash-uncensored","name":"GLM 5.3 Flash Uncensored","description":"GLM 5.3 Flash Uncensored is an uncensored fine-tune of the efficient 320B mixture-of-experts reasoning model, built for unrestricted chat, creative writing, coding, agentic work, tool use, and long-context tasks.","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-07-29","last_updated":"2026-08-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":32768},"cost":{"input":0.2,"output":0.8,"cache_read":0.07},"display_name":"GLM 5.3 Flash Uncensored","type":"chat"},{"id":"z-ai/glm-4.6","name":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.5,"output":2,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.7-flash:thinking","name":"GLM 4.7 Flash Thinking","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM 4.7 Flash Thinking","type":"chat"},{"id":"z-ai/glm-5.3-flash-apex","name":"Apex Flash 1","description":"Apex Flash 1 is Cantina Security and Yeta's cybersecurity-focused post-train of GLM 5.3 Flash for code investigation and tool use.","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":32768},"cost":{"input":0.15,"output":0.5,"cache_read":0.075},"display_name":"Apex Flash 1","type":"chat"},{"id":"z-ai/glm-5-original:thinking","name":"GLM 5 Original Thinking","description":"GLM-5 original with extended thinking capabilities for complex reasoning.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.6,"output":1.9,"cache_read":0.1},"display_name":"GLM 5 Original Thinking","type":"chat"},{"id":"z-ai/glm-5.3:thinking","name":"GLM 5.3 Thinking","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 Thinking","type":"chat"},{"id":"z-ai/glm-5","name":"GLM 5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.6,"output":1.9,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/GLM-4.5-Air","name":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":98304},"cost":{"input":0.12,"output":0.8,"cache_read":0.06},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM 4.5 Air","type":"chat"},{"id":"z-ai/glm-4.5v","name":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.3},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM 4.5V","type":"chat"},{"id":"z-ai/GLM-4.6-turbo:thinking","name":"GLM 4.6 Turbo (Thinking)","description":"GLM 4.6 Turbo with thinking mode enabled for enhanced reasoning; shows internal reasoning and supports long context.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":1,"output":3,"cache_read":0.5},"display_name":"GLM 4.6 Turbo (Thinking)","type":"chat"},{"id":"z-ai/glm-4.7:thinking","name":"GLM 4.7 Thinking","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.4004,"output":1.9292,"cache_read":0.08008},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM 4.7 Thinking","type":"chat"},{"id":"z-ai/glm-5.1:thinking","name":"GLM 5.1 Thinking","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.7,"output":2.5,"cache_read":0.18},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1 Thinking","type":"chat"},{"id":"z-ai/glm-4.6v-original","name":"GLM 4.6V Original","description":"GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Direct via Z-AI (Zhipu).","family":"glm","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":24000},"cost":{"input":0.6,"output":0.9,"cache_read":0.3},"display_name":"GLM 4.6V Original","type":"chat"},{"id":"z-ai/glm-5v-turbo:thinking","name":"GLM 5V Turbo Thinking","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"input":202800,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM 5V Turbo Thinking","type":"chat"},{"id":"z-ai/GLM-4.6-turbo","name":"GLM 4.6 Turbo","description":"Fast variant of GLM 4.6 for general chat, coding, and analysis with improved latency and strong reasoning.","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":1,"output":3,"cache_read":0.5},"display_name":"GLM 4.6 Turbo","type":"chat"},{"id":"z-ai/GLM-4.5-Air:thinking","name":"GLM 4.5 Air (Thinking)","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":98304},"cost":{"input":0.12,"output":0.8,"cache_read":0.06},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM 4.5 Air (Thinking)","type":"chat"},{"id":"z-ai/glm-5.2:thinking","name":"GLM 5.2 Thinking","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.189,"output":0.594,"cache_read":0.0351},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Thinking","type":"chat"},{"id":"z-ai/glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM 4.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.7","name":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.4004,"output":1.9292,"cache_read":0.08008},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.3-uncensored","name":"GLM 5.3 Uncensored","description":"An experimental uncensored version of the full GLM 5.3 reasoning model for chat, creative writing, coding, and tool use. It may show unusual behavior or inconsistent response quality.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-09-26","last_updated":"2026-09-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.25,"output":2.25,"cache_read":0.3},"display_name":"GLM 5.3 Uncensored","type":"chat"},{"id":"z-ai/glm-5:thinking","name":"GLM 5 Thinking","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.6,"output":1.9,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM 5 Thinking","type":"chat"},{"id":"z-ai/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.189,"output":0.594,"cache_read":0.0351},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/GLM-4.5:thinking","name":"GLM 4.5 (Thinking)","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.3,"output":1.3,"cache_read":0.15},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM 4.5 (Thinking)","type":"chat"},{"id":"z-ai/glm-5.1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.7,"output":2.5,"cache_read":0.18},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.6:thinking","name":"GLM 4.6 Thinking","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.5,"output":2,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM 4.6 Thinking","type":"chat"},{"id":"z-ai/glm-4.5v:thinking","name":"GLM 4.5V Thinking","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.3},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM 4.5V Thinking","type":"chat"},{"id":"z-ai/glm-4.7-original","name":"GLM 4.7 Original","description":"GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use. Routed directly via Z-AI (Zhipu).","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"display_name":"GLM 4.7 Original","type":"chat"},{"id":"z-ai/glm-5-original","name":"GLM 5 Original","description":"GLM-5 is Zhipu's latest flagship model with advanced reasoning and instruction following. Routed directly via Z-AI (Zhipu).","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.6,"output":1.9,"cache_read":0.1},"display_name":"GLM 5 Original","type":"chat"},{"id":"z-ai/glm-5-turbo","name":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"input":202800,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM 5 Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.7-original:thinking","name":"GLM 4.7 Original Thinking","description":"GLM-4.7 original with extended thinking capabilities for complex reasoning.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"display_name":"GLM 4.7 Original Thinking","type":"chat"},{"id":"z-ai/glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flash-cybersecurity","name":"GLM 5.3 Flash Cybersecurity","description":"GLM 5.3 Flash Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports always-on reasoning, image understanding, tool calling, and a 1,048,576-token context window.","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-09-19","last_updated":"2026-09-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":32768},"cost":{"input":0.15,"output":0.5,"cache_read":0.075},"display_name":"GLM 5.3 Flash Cybersecurity","type":"chat"},{"id":"z-ai/glm-latest","name":"GLM Latest","description":"Compatibility alias that routes to the newest thinking GLM model. Currently routes to GLM 5.2 Thinking.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"display_name":"GLM Latest","type":"chat"},{"id":"reflection/beam-1.0","name":"Beam 1.0 501B A23B","description":"Reflection's Apache 2.0 open-weight text model with 501.3B total and 23.4B active parameters, built for coding, reasoning and tool use. It supports a shared 1,048,576-token context window, up to 131,072 output tokens, JSON mode and structured output. Reasoning is always enabled with low, medium, high, xhigh and max effort; NanoGPT defaults to max. Knowledge cutoff: June 30, 2026.","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"display_name":"Beam 1.0 501B A23B","type":"chat"},{"id":"inference-net/schematron-v2-small","name":"Schematron V2 Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-09-12","last_updated":"2026-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":0.05,"output":0.23,"cache_read":0.025},"canonical_model_id":"inference-net/schematron-v2-small","display_name":"Schematron V2 Small","type":"chat"},{"id":"inference-net/schematron-v2-turbo","name":"Schematron V2 Turbo","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-09-12","last_updated":"2026-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.03,"output":0.15,"cache_read":0.015},"canonical_model_id":"inference-net/schematron-v2-turbo","display_name":"Schematron V2 Turbo","type":"chat"},{"id":"thinkingmachines/inkling:thinking","name":"Inkling Thinking","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"input":1048000,"output":32768},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling Thinking","type":"chat"},{"id":"thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat"},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"input":1048000,"output":32768},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"thinkingmachines/Inkling-Small:thinking","name":"Inkling Small Thinking","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small Thinking","type":"chat"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":943718},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":117964},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat"},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor (Data Used for Training)","description":"A much cheaper opt-in version of Muse Spark 1.2 with the same multimodal coding and agentic capabilities. Prompts and outputs sent to this Contributor model may be used by Meta for training and to improve its products; use the standard Muse Spark 1.2 model if you do not want your data used for training.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.2 Contributor (Data Used for Training)","type":"chat"},{"id":"meta/muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","description":"Meta's Muse Spark 1.3 Contributor is a frontier multimodal reasoning model for long-horizon coding and agentic workflows, with strong gains in computer use, browsing, professional tool use, codebase understanding, and million-token retrieval. It accepts text, images, audio, video, and files, supports tool calling and structured output, and always reasons before answering. Prompts and outputs may be used by Meta for training and to improve its products.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":943718},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.3 Contributor","type":"chat"},{"id":"meta/muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"mlabonne/NeuralDaredevil-8B-abliterated","name":"Neural Daredevil 8B abliterated","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":0.44,"output":0.44,"cache_read":0.22},"display_name":"Neural Daredevil 8B abliterated","type":"chat"},{"id":"NeverSleep/Lumimaid-v0.2-70B","name":"Lumimaid v0.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":1,"output":1.5,"cache_read":0.5},"display_name":"Lumimaid v0.2","type":"chat"},{"id":"nanogpt/coding-router:low","name":"Coding Router Low","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"display_name":"Coding Router Low","type":"chat"},{"id":"nanogpt/coding-router:medium","name":"Coding Router Medium","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"display_name":"Coding Router Medium","type":"chat"},{"id":"nanogpt/coding-router","name":"Coding Router","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":1.1,"output":2.2,"cache_read":0.11},"display_name":"Coding Router","type":"chat"},{"id":"nanogpt/coding-router:max","name":"Coding Router Max","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"display_name":"Coding Router Max","type":"chat"},{"id":"nanogpt/coding-router:high","name":"Coding Router High","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":1.1,"output":2.2,"cache_read":0.11},"display_name":"Coding Router High","type":"chat"},{"id":"LatitudeGames/Wayfarer-Large-70B-Llama-3.3","name":"Llama 3.3 70B Wayfarer","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"display_name":"Llama 3.3 70B Wayfarer","type":"chat"},{"id":"VongolaChouko/Starcannon-Unleashed-12B-v1.0","name":"Mistral Nemo Starcannon 12b v1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Mistral Nemo Starcannon 12b v1","type":"chat"},{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":80000},"cost":{"input":0.25,"output":0.9,"cache_read":0.125},"canonical_model_id":"arcee-ai/trinity-large-thinking","display_name":"Trinity Large Thinking","type":"chat"},{"id":"x-ai/grok-4.20-multi-agent","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"input":2000000,"output":131072},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"display_name":"Grok 4.20 Multi-Agent","type":"chat"},{"id":"x-ai/grok-latest","name":"Grok Latest","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":500000,"output":450000},"cost":{"input":2,"output":6,"cache_read":0.5},"display_name":"Grok Latest","type":"chat"},{"id":"x-ai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":900000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":500000,"output":450000},"cost":{"input":2,"output":6,"cache_read":0.3},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":230400},"cost":{"input":1,"output":2,"cache_read":0.2},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.20","name":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"input":2000000,"output":131072},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"display_name":"Grok 4.20","type":"chat"},{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":500000,"output":450000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"elorian/glimpse","name":"Elorian Glimpse","description":"Glimpse is Elorian's visual reasoning model for understanding images and video and answering in text. It can analyze charts, count objects, follow events over time, and reason about spatial relationships and physical cause and effect. It supports tool calling and structured output across a shared 262,144-token context window, with up to 256,000 output tokens within the remaining context.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":256000},"cost":{"input":0.63,"output":3.15,"cache_read":0.063},"display_name":"Elorian Glimpse","type":"chat"},{"id":"Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B","name":"Nemotron Tenyxchat Storybreaker 70b","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Nemotron Tenyxchat Storybreaker 70b","type":"chat"},{"id":"Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B","name":"Llama 3.05 Storybreaker Ministral 70b","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Llama 3.05 Storybreaker Ministral 70b","type":"chat"},{"id":"heabsy/qwen3.8-27b-uncensored-fast","name":"Qwen 3.8 27B Uncensored Fast by Heabsy","description":"Heabsy's NVFP4 build of Qwen3.8-27B by Alibaba Cloud, with refusal removal based on huihui-ai's Huihui-Qwen3.8-27B-abliterated. Quantized and calibrated by Heabsy, with unpublished weights under the Heabsy Model License. Supports text and image input, tools, and optional reasoning capped at 16,384 tokens within the output budget. This named build is separate from Qwen 3.8 27B Uncensored.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":235929},"cost":{"input":1,"output":3,"cache_read":0.22},"display_name":"Qwen 3.8 27B Uncensored Fast by Heabsy","type":"chat"},{"id":"heabsy/cyberheabsy","name":"CyberHeabsy","description":"A low-refusal text model for authorized security research, roleplay, and creative writing. It preserves tool calling after refusal removal, supports optional reasoning, and has a 1M-token context window.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-09-27","last_updated":"2026-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":1.5,"output":4.5,"cache_read":0.275},"display_name":"CyberHeabsy","type":"chat"},{"id":"upstage/solar-pro-3","name":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":117964},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Solar Pro 3","type":"chat"},{"id":"upstage/solar-pro4","name":"Solar Pro 4","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":131072},"cost":{"input":0.03,"output":0.12,"cache_read":0.006},"canonical_model_id":"upstage/solar-pro4","display_name":"Solar Pro 4","type":"chat"},{"id":"upstage/solar-mini4:thinking","name":"Solar Mini 4 Thinking","description":"Solar Mini 4 with reasoning enabled for agentic tasks and harder analysis across a 524K-token context window.","family":"solar","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":131072},"cost":{"input":0.05,"output":0.2,"cache_read":0.005},"display_name":"Solar Mini 4 Thinking","type":"chat"},{"id":"upstage/solar-pro4:thinking","name":"Solar Pro 4 Thinking","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":131072},"cost":{"input":0.03,"output":0.12,"cache_read":0.006},"canonical_model_id":"upstage/solar-pro4","display_name":"Solar Pro 4 Thinking","type":"chat"},{"id":"upstage/solar-mini4","name":"Solar Mini 4","description":"Upstage's compact 35B-parameter mixture-of-experts model with 3B active parameters and a 524K context window. Built for fast, cost-efficient agentic tasks, with strong Korean and English support.","family":"solar","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":131072},"cost":{"input":0.05,"output":0.2,"cache_read":0.005},"display_name":"Solar Mini 4","type":"chat"},{"id":"bytedance/doubao-seed-2.1-turbo","name":"Doubao Seed 2.1 Turbo","description":"Fast, lower-cost model in the Doubao Seed 2.1 family for everyday chat, coding assistance, document work, and high-throughput productivity tasks. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"display_name":"Doubao Seed 2.1 Turbo","type":"chat"},{"id":"bytedance/doubao-seed-2.1-pro","name":"Doubao Seed 2.1 Pro","description":"Higher-capability model in the Doubao Seed 2.1 family for agentic coding, long-context analysis, complex instruction following, and productivity workflows. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":1,"output":5,"cache_read":0.5},"display_name":"Doubao Seed 2.1 Pro","type":"chat"},{"id":"bytedance/doubao-seed-character","name":"Doubao Seed Character","description":"ByteDance's character-focused Doubao Seed model for roleplay, persona consistency, dialogue, and creative character interactions. It supports text and image input with a 128k context window. Requests route through ZenMux to ByteDance; ZenMux does not publish a model-API zero-retention or training guarantee, so avoid sensitive data.","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"release_date":"2026-07-18","last_updated":"2026-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":0.15,"output":0.37,"cache_read":0.03,"cache_write":0.003},"display_name":"Doubao Seed Character","type":"chat"},{"id":"liquid/lfm-2.5-2.6b","name":"LFM2.5 2.6B","description":"Liquid AI's compact 2.6B reasoning model for agent workflows, data extraction, RAG, and long-context processing. It supports tool calling and structured output, but Liquid advises against using it for agentic coding. Warning: prompts and responses may be logged and used for model training or service improvement; do not send sensitive data.","family":"liquid","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":0.1,"output":0.2,"cache_read":0.05},"display_name":"LFM2.5 2.6B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"liquid/lfm-2.5-24b-a2b","name":"LFM2.5 24B A2B","description":"Liquid AI's text-only mixture-of-experts model for reasoning and tool-using agents, with 24B total and 2.45B active parameters. It always thinks before answering and supports structured output. Pair it with retrieval for knowledge-heavy tasks. Open weights use the LFM Open License v1.0, with a $10M annual-revenue commercial threshold; hosted API use is subject to separate service terms that permit retention and use of prompts and responses for model training.","family":"liquid","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-10-14","last_updated":"2026-10-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.05,"output":0.7,"cache_read":0.025},"display_name":"LFM2.5 24B A2B","type":"chat"},{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-flash-latest","display_name":"Gemini Flash Latest","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.14,"output":0.4,"cache_read":0.05},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B","type":"chat"},{"id":"google/gemini-3.1-pro-preview-low","name":"Gemini 3.1 Pro (Preview Low)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-02-21","last_updated":"2026-02-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"display_name":"Gemini 3.1 Pro (Preview Low)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash-thinking","name":"Gemini 3.5 Flash Thinking","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-4-26b-a4b-it:thinking","name":"Gemma 4 26B A4B Thinking","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.0675,"output":0.225,"cache_read":0.0375},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B Thinking","type":"chat"},{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"canonical_model_id":"google/gemini-flash-lite-latest","display_name":"Gemini Flash Lite Latest","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/diffusiongemma","name":"DiffusionGemma","description":"DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","xhigh"]}],"tool_call":false,"structured_output":false,"release_date":"2026-09-19","last_updated":"2026-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.05,"output":0.15,"cache_read":0.025},"display_name":"DiffusionGemma","type":"chat"},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.0675,"output":0.225,"cache_read":0.0375},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B","type":"chat"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemma-4-31b-it:thinking","name":"Gemma 4 31B Thinking","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.1,"output":0.34,"cache_read":0.1},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B Thinking","type":"chat"},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro (Preview)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-high","name":"Gemini 3.1 Pro (Preview High)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-02-21","last_updated":"2026-02-21","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"display_name":"Gemini 3.1 Pro (Preview High)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma4-31b-splituntied","name":"Gemma 4 31B Split-Untied","description":"Blazed-Forge's Split-Untied is a text-only Gemma 4 31B community finetune with an untied BF16 output head, built for creative writing, roleplay, expressive dialogue, and tool use.","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"display_name":"Gemma 4 31B Split-Untied","type":"chat"},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-4-26b-a4b-it-cybersecurity","name":"Gemma 4 26B A4B Cybersecurity","description":"Gemma 4 26B A4B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-19","last_updated":"2026-09-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1056,"output":0.3344,"cache_read":0.0528},"display_name":"Gemma 4 26B A4B Cybersecurity","type":"chat"},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro (Preview Custom Tools)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro (Preview Custom Tools)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash (Preview)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash (Preview)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-pro-latest","name":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"display_name":"Gemini Pro Latest","type":"chat"},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview-thinking","name":"Gemini 3 Flash Thinking","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":0.1875},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/gemma-4-31b-it","name":"Gemma 4 31B IT TEE","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.15,"output":0.46,"cache_read":0.075},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT TEE","type":"chat"},{"id":"TEE/qwen3.8-27b","name":"Qwen3.8 27B TEE","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.4,"output":3,"cache_read":0.15},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B TEE","type":"chat"},{"id":"TEE/nemotron-3.5-lightning","name":"Nvidia Nemotron 3.5 Lightning TEE","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.08,"output":0.2,"cache_read":0.04},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nvidia Nemotron 3.5 Lightning TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/glm-5.3-flash","name":"GLM 5.3 Flash TEE","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/qwen3.5-27b","name":"Qwen3.5 27B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.3,"output":2.4,"cache_read":0.15},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"TEE/muse-glimmer-30b","name":"Muse Glimmer 30B TEE","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B TEE","type":"chat"},{"id":"TEE/kimi-k3","name":"Kimi K3 TEE","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":65535},"cost":{"input":3,"output":15,"cache_read":1.5},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash TEE","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.65,"output":1.45,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/llama3-3-70b","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-03","last_updated":"2025-07-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":1.75,"output":2.75,"cache_read":1.75},"display_name":"Llama 3.3 70B","type":"chat"},{"id":"TEE/kimi-k2.6","name":"Kimi K2.6 TEE","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":1.5,"output":5.25,"cache_read":0.375},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/gemma-4-26b-a4b-uncensored","name":"Gemma 4 26B A4B Uncensored TEE","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-05-23","last_updated":"2026-05-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":65536},"cost":{"input":0.15,"output":0.7,"cache_read":0.075},"display_name":"Gemma 4 26B A4B Uncensored TEE","type":"chat"},{"id":"TEE/gemma4-31b:thinking","name":"Gemma 4 31B Thinking TEE","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-02","last_updated":"2026-05-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.4,"output":1,"cache_read":0.4},"display_name":"Gemma 4 31B Thinking TEE","type":"chat"},{"id":"TEE/gemma4-31b","name":"Gemma 4 31B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-04-04","last_updated":"2026-04-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.4,"output":1,"cache_read":0.4},"display_name":"Gemma 4 31B","type":"chat"},{"id":"TEE/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B TEE","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.2,"output":1.27,"cache_read":0.1},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"TEE/glm-5.2:thinking","name":"GLM 5.2 Thinking TEE","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.7},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Thinking TEE","type":"chat"},{"id":"TEE/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B TEE","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.55,"output":3.5,"cache_read":0.275},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B A17B TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"TEE/glm-5.2","name":"GLM 5.2 TEE","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.7},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/glm-5.1-thinking","name":"GLM 5.1 Thinking TEE","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"input":202752,"output":65535},"cost":{"input":0.7,"output":2.5,"cache_read":0.18},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1 Thinking TEE","type":"chat"},{"id":"TEE/glm-5.1","name":"GLM 5.1 TEE","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"input":202752,"output":65535},"cost":{"input":0.7,"output":2.5,"cache_read":0.18},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/qwen2.5-vl-72b-instruct","name":"Qwen2.5 VL 72B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"display_name":"Qwen2.5 VL 72B TEE","type":"chat"},{"id":"TEE/qwen3.6-27b","name":"Qwen3.6 27B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.32,"output":2.7,"cache_read":0.16},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"TEE/deepseek-v3.2","name":"DeepSeek V3.2 TEE","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"input":164000,"output":65536},"cost":{"input":0.5,"output":1,"cache_read":0.25},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/gpt-oss-120b","name":"GPT-OSS 120B TEE","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":2,"output":2,"cache_read":2},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT-OSS 120B TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/glm-5.3","name":"GLM 5.3 TEE","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"TEE/kimi-k2.7-code","name":"Kimi K2.7 Code TEE","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2","name":"EVA-Qwen2.5-72B-v0.2","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.799,"output":0.799,"cache_read":0.3995},"display_name":"EVA-Qwen2.5-72B-v0.2","type":"chat"},{"id":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0","name":"EVA Llama 3.33 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":2.006,"output":2.006,"cache_read":1.003},"display_name":"EVA Llama 3.33 70B","type":"chat"},{"id":"EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2","name":"EVA-Qwen2.5-32B-v0.2","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.799,"output":0.799,"cache_read":0.3995},"display_name":"EVA-Qwen2.5-32B-v0.2","type":"chat"},{"id":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1","name":"EVA-LLaMA-3.33-70B-v0.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":2.006,"output":2.006,"cache_read":1.003},"display_name":"EVA-LLaMA-3.33-70B-v0.1","type":"chat"},{"id":"nothingiisreal/L3.1-70B-Celeste-V0.1-BF16","name":"Llama 3.1 70B Celeste v0.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Llama 3.1 70B Celeste v0.1","type":"chat"},{"id":"aisingapore/Gemma-SEA-LION-v4-27B-IT","name":"Gemma SEA-LION v4 27B","description":"Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":128000},"cost":{"input":0.24,"output":0.48},"canonical_model_id":"aisingapore/gemma-sea-lion-v4-27b-it","display_name":"Gemma SEA-LION v4 27B","type":"chat"},{"id":"MarinaraSpaghetti/NemoMix-Unleashed-12B","name":"NemoMix 12B Unleashed","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"NemoMix 12B Unleashed","type":"chat"},{"id":"pamanseau/OpenReasoning-Nemotron-32B","name":"OpenReasoning Nemotron 32B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"display_name":"OpenReasoning Nemotron 32B","type":"chat"},{"id":"huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated","name":"DeepSeek R1 Qwen Abliterated","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":1.4,"output":1.4,"cache_read":0.7},"display_name":"DeepSeek R1 Qwen Abliterated","type":"chat"},{"id":"huihui-ai/Qwen2.5-32B-Instruct-abliterated","name":"Qwen 2.5 32B Abliterated","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-01-06","last_updated":"2025-01-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"display_name":"Qwen 2.5 32B Abliterated","type":"chat"},{"id":"huihui-ai/Llama-3.3-70B-Instruct-abliterated","name":"Llama 3.3 70B Instruct abliterated","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"display_name":"Llama 3.3 70B Instruct abliterated","type":"chat"},{"id":"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","name":"DeepSeek R1 Llama 70B Abliterated","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"display_name":"DeepSeek R1 Llama 70B Abliterated","type":"chat"},{"id":"Gryphe/MythoMax-L2-13b","name":"MythoMax 13B","description":"Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2023-08-10","last_updated":"2023-08-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"input":4096,"output":3686},"cost":{"input":0.1003,"output":0.1003,"cache_read":0.05015},"canonical_model_id":"gryphe/mythomax-l2-13b","display_name":"MythoMax 13B","type":"chat"},{"id":"moondream/moondream3-preview","name":"Moondream 3 Preview","description":"Moondream 3 Preview is the original 9B mixture-of-experts vision-language checkpoint with 2B active parameters, for visual question answering, captioning, OCR, and visual reasoning. It accepts text or one image with optional reasoning, a 32,000-token context, and up to 4,096 output tokens.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":4096},"cost":{"input":0.3,"output":2.5},"display_name":"Moondream 3 Preview","type":"chat"},{"id":"moondream/moondream3.1-9b-a2b","name":"Moondream 3.1 9B A2B","description":"Moondream 3.1 is the successor to Moondream 3 Preview: a distinct 9B mixture-of-experts vision-language checkpoint with 2B active parameters, for visual question answering, captioning, OCR, and visual reasoning. It accepts text or one image with optional reasoning, a 32,000-token context, and up to 4,096 output tokens.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":4096},"cost":{"input":0.3,"output":2.5},"display_name":"Moondream 3.1 9B A2B","type":"chat"},{"id":"ibm-granite/granite-4.2-8b","name":"Granite 4.2 8B","description":"IBM Granite 4.2 8B is an Apache 2.0-licensed dense model with native step-by-step reasoning and specialized training for agentic work. It can plan before acting, sequence tools, navigate codebases, work in terminals, and verify results across coding, search, mathematics, science, and complex instruction-following tasks.","family":"granite","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-31","last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":117964},"cost":{"input":0.1,"output":0.15,"cache_read":0.05},"display_name":"Granite 4.2 8B","type":"chat"},{"id":"TheDrummer/skyfall-36b-v2","name":"TheDrummer Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06-30","release_date":"2025-03-10","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":29491},"cost":{"input":0.55,"output":0.8,"cache_read":0.25},"canonical_model_id":"thedrummer/skyfall-36b-v2","display_name":"TheDrummer Skyfall 36B V2","type":"chat"},{"id":"TheDrummer/Artemis-v1.1","name":"TheDrummer/Artemis v1.1","description":"TheDrummer's Artemis v1.1 is a Gemma 4 31B fine-tune for creative writing, expressive dialogue, and roleplay, with optional thinking and a 262K context window.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-06","last_updated":"2026-09-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"TheDrummer/Artemis v1.1","type":"chat"},{"id":"TheDrummer/Anubis-70B-v1","name":"Anubis 70B v1","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":16384},"cost":{"input":0.31,"output":0.31,"cache_read":0.155},"display_name":"Anubis 70B v1","type":"chat"},{"id":"TheDrummer/Anubis-70B-v1.1","name":"Anubis 70B v1.1","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":16384},"cost":{"input":0.31,"output":0.31,"cache_read":0.155},"display_name":"Anubis 70B v1.1","type":"chat"},{"id":"TheDrummer/Cydonia-24B-v4.3","name":"The Drummer Cydonia 24B v4.3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-25","last_updated":"2025-12-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.12,"output":0.15,"cache_read":0.06},"display_name":"The Drummer Cydonia 24B v4.3","type":"chat"},{"id":"TheDrummer/Magidonia-24B-v4.3","name":"The Drummer Magidonia 24B v4.3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-25","last_updated":"2025-12-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.1003,"output":0.1207,"cache_read":0.05015},"display_name":"The Drummer Magidonia 24B v4.3","type":"chat"},{"id":"TheDrummer/Cydonia-24B-v4.1","name":"The Drummer Cydonia 24B v4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04-30","release_date":"2025-09-27","last_updated":"2025-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":117964},"cost":{"input":0.3,"output":0.5,"cache_read":0.15},"canonical_model_id":"thedrummer/cydonia-24b-v4.1","display_name":"The Drummer Cydonia 24B v4.1","type":"chat"},{"id":"TheDrummer/UnslopNemo-12B-v4.1","name":"UnslopNemo 12b v4","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"input":8192,"output":26214},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"UnslopNemo 12b v4","type":"chat"},{"id":"TheDrummer/Cydonia-24B-v2","name":"The Drummer Cydonia 24B v2","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.1003,"output":0.1207,"cache_read":0.05015},"display_name":"The Drummer Cydonia 24B v2","type":"chat"},{"id":"TheDrummer/Rocinante-12B-v1.1","name":"Rocinante 12b","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.408,"output":0.595,"cache_read":0.204},"display_name":"Rocinante 12b","type":"chat"},{"id":"TheDrummer/Cydonia-24B-v4","name":"The Drummer Cydonia 24B v4","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.2006,"output":0.2414,"cache_read":0.1003},"display_name":"The Drummer Cydonia 24B v4","type":"chat"},{"id":"TheDrummer/orion-26b-a4b-v1.1","name":"Orion 26B A4B v1.1","description":"TheDrummer's Gemma 4 26B A4B fine-tune for creative writing, roleplay, and expressive dialogue. Supports optional thinking with a 65,536-token context window and up to 8,192 output tokens. Text input only.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.1,"output":0.45,"cache_read":0.05},"display_name":"Orion 26B A4B v1.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.2,"output":0.7,"cache_read":0.1},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek-ai/deepseek-v3.2-exp-thinking","name":"DeepSeek V3.2 Exp Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"input":163840,"output":65536},"cost":{"input":0.28,"output":0.42,"cache_read":0.14},"display_name":"DeepSeek V3.2 Exp Thinking","type":"chat"},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"input":163840,"output":32768},"cost":{"input":0.5,"output":2.15,"cache_read":0.35},"display_name":"DeepSeek R1 0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-08-02","last_updated":"2025-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.25,"output":0.7,"cache_read":0.125},"display_name":"DeepSeek V3.1 Terminus","type":"chat"},{"id":"deepseek-ai/deepseek-v3.2-exp","name":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"input":163840,"output":65536},"cost":{"input":0.28,"output":0.42,"cache_read":0.14},"display_name":"DeepSeek V3.2 Exp","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1:thinking","name":"DeepSeek V3.1 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.2,"output":0.7,"cache_read":0.1},"display_name":"DeepSeek V3.1 Thinking","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1-Terminus:thinking","name":"DeepSeek V3.1 Terminus (Thinking)","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.25,"output":0.7,"cache_read":0.125},"display_name":"DeepSeek V3.1 Terminus (Thinking)","type":"chat"},{"id":"stepfun-ai/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"canonical_model_id":"stepfun/step-3.5-flash-2603","display_name":"Step 3.5 Flash 2603","type":"chat"},{"id":"stepfun-ai/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash","type":"chat"},{"id":"MiniMaxAI/MiniMax-M1-80k","name":"MiniMax M1 80K","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-01-08","last_updated":"2025-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.6052,"output":2.4225,"cache_read":0.3026},"display_name":"MiniMax M1 80K","type":"chat"},{"id":"fireworks/ember-1","name":"Ember 1","description":"Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"fireworks/ember-1","display_name":"Ember 1","type":"chat"},{"id":"mistralai/ministral-8b-2512","name":"Ministral 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.075},"canonical_model_id":"mistral/ministral-8b-2512","display_name":"Ministral 8B","type":"chat"},{"id":"mistralai/mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":262144},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"mistralai/mistral-small-4-119b-2603:thinking","name":"Mistral Small 4 119B Thinking","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.4,"output":1.4,"cache_read":0.2},"display_name":"Mistral Small 4 119B Thinking","type":"chat"},{"id":"mistralai/mistral-medium-3.5","name":"Mistral Medium 3.5","description":"Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.5,"output":7.5,"cache_read":0.75},"display_name":"Mistral Medium 3.5","type":"chat"},{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral Small 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.1155,"output":0.3465},"canonical_model_id":"mistral/mistral-small-24b-instruct-2501","display_name":"Mistral Small 24B","type":"chat"},{"id":"mistralai/mixtral-8x22b-instruct-v0.1","name":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mixtral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":52428},"cost":{"input":2,"output":6,"cache_read":0.2},"display_name":"Mixtral 8x22B","type":"chat"},{"id":"mistralai/mistral-saba","name":"Mistral Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":26214},"cost":{"input":0.1989,"output":0.595,"cache_read":0.09945},"canonical_model_id":"mistral/mistral-saba","display_name":"Mistral Saba","type":"chat"},{"id":"mistralai/mistral-medium-3.1","name":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.4,"output":2,"cache_read":0.2},"canonical_model_id":"mistral/mistral-medium-3.1","display_name":"Mistral Medium 3.1","type":"chat"},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral Small 3.2 24B (2506)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.2,"output":0.4,"cache_read":0.1},"canonical_model_id":"mistral/mistral-small-3.2-24b-instruct","display_name":"Mistral Small 3.2 24B (2506)","type":"chat"},{"id":"mistralai/mistral-small-4-119b-2603","name":"Mistral Small 4 119B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.4,"output":1.4,"cache_read":0.2},"display_name":"Mistral Small 4 119B","type":"chat"},{"id":"mistralai/mistral-large","name":"Mistral Large 2411","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-11-30","release_date":"2024-02-26","last_updated":"2024-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":102400},"cost":{"input":2.006,"output":6.001,"cache_read":0.2},"canonical_model_id":"mistral/mistral-large","display_name":"Mistral Large 2411","type":"chat"},{"id":"mistralai/mistral-medium-3.5:thinking","name":"Mistral Medium 3.5 Thinking","description":"Mistral Medium 3.5 with reasoning enabled by default (reasoning_effort=high), for complex coding, agentic, and multi-step reasoning prompts.","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.5,"output":7.5,"cache_read":0.75},"display_name":"Mistral Medium 3.5 Thinking","type":"chat"},{"id":"mistralai/devstral-small-2505","name":"Mistral Devstral Small 2505","description":"OpenHands+Devstral is 100% local 100% open, and is SOTA for the category on SWE-Bench Verified: 46.8% accuracy.","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-08-02","last_updated":"2025-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.06,"output":0.06,"cache_read":0.03},"display_name":"Mistral Devstral Small 2505","type":"chat"},{"id":"mistralai/devstral-2-123b-instruct-2512","name":"Devstral 2 123B","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.4,"output":1.4,"cache_read":0.2},"display_name":"Devstral 2 123B","type":"chat"},{"id":"mistralai/mistral-medium-3","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.4,"output":2,"cache_read":0.2},"canonical_model_id":"mistral/mistral-medium-3","display_name":"Mistral Medium 3","type":"chat"},{"id":"mistralai/ministral-14b-instruct-2512","name":"Ministral 3 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"display_name":"Ministral 3 14B","type":"chat"},{"id":"mistralai/ministral-14b-2512","name":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"canonical_model_id":"mistral/ministral-14b-2512","display_name":"Ministral 14B","type":"chat"},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B (2503)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":102400},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"canonical_model_id":"mistral/mistral-small-3.1-24b-instruct","display_name":"Mistral Small 3.1 24B (2503)","type":"chat"},{"id":"mistralai/ministral-3b-2512","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.05},"canonical_model_id":"mistral/ministral-3b-2512","display_name":"Ministral 3B","type":"chat"},{"id":"mistralai/mistral-nemo-instruct-2407","name":"Mistral Nemo","description":"12B parameter model with multilingual support.","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.1003,"output":0.1207,"cache_read":0.05015},"display_name":"Mistral Nemo","type":"chat"},{"id":"mistralai/codestral-2508","name":"Codestral 2508","description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.15},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 2508","type":"chat"},{"id":"sakana/fugu-max","name":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"sakana/fugu-max","display_name":"Fugu Max","type":"chat"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":16384},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"sakana/fugu-ultra-v1.1","name":"Fugu Ultra v1.1","description":"Sakana AI's upgraded Fugu Ultra release with stronger coding, agentic task execution, and advanced reasoning through dynamic orchestration of frontier models.","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":16384},"cost":{"input":5,"output":30,"cache_read":0.5},"display_name":"Fugu Ultra v1.1","type":"chat"},{"id":"inclusionai/ling-3.0-flash","name":"Ling 3.0 Flash","description":"Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents","family":"ling","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"canonical_model_id":"inclusionai/ling-3.0-flash","display_name":"Ling 3.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionai/ling-3.1-flash","name":"Ling 3.1 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"canonical_model_id":"inclusionai/ling-3.1-flash","display_name":"Ling 3.1 Flash","type":"chat"},{"id":"inclusionai/ling-3.0-flash-vl","name":"Ling 3.0 Flash VL","description":"Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"canonical_model_id":"inclusionai/ling-3.0-flash-vl","display_name":"Ling 3.0 Flash VL","type":"chat"},{"id":"inclusionai/ling-3.0-flash:thinking","name":"Ling 3.0 Flash Thinking","description":"Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"canonical_model_id":"inclusionai/ling-3.0-flash","display_name":"Ling 3.0 Flash Thinking","type":"chat"},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":943718},"cost":{"input":0.504,"output":8.1,"cache_read":0.18},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code High-Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":1.9,"output":8,"cache_read":0.32},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code High-Speed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.43225,"output":1.82,"cache_read":0.0728},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.5:thinking","name":"Kimi K2.5 Thinking","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.375,"output":2,"cache_read":0.07},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 Thinking","type":"chat"},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":98304},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.375,"output":2,"cache_read":0.07},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","description":"Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":8192},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"canonical_model_id":"moonshotai/kimi-k2-instruct","display_name":"Kimi K2 Instruct","type":"chat"},{"id":"moonshotai/kimi-k2.6:thinking","name":"Kimi K2.6 Thinking","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.43225,"output":1.82,"cache_read":0.0728},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 Thinking","type":"chat"},{"id":"moonshotai/kimi-k2-instruct-0711","name":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"display_name":"Kimi K2 0711","type":"chat"},{"id":"moonshotai/kimi-latest","name":"Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":943718},"cost":{"input":0.504,"output":8.1,"cache_read":0.18},"display_name":"Kimi Latest","type":"chat"},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.6712,"output":3.35,"cache_read":0.18},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":100352},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"display_name":"Kimi K2 0905","type":"chat"},{"id":"THUDM/GLM-Z1-9B-0414","name":"GLM Z1 9B 0414","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm-z","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8000},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"display_name":"GLM Z1 9B 0414","type":"chat"},{"id":"THUDM/GLM-4-9B-0414","name":"GLM 4 9B 0414","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8000},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"display_name":"GLM 4 9B 0414","type":"chat"},{"id":"THUDM/GLM-4-32B-0414","name":"GLM 4 32B 0414","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"display_name":"GLM 4 32B 0414","type":"chat"},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nvidia Nemotron 3 Nano 30B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":235929},"cost":{"input":0.17,"output":0.68,"cache_read":0.085},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nvidia Nemotron 3 Nano 30B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-lightning","name":"Nvidia Nemotron 3.5 Lightning","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nvidia Nemotron 3.5 Lightning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1","name":"Nvidia Nemotron Super 49B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.15,"output":0.15,"cache_read":0.075},"canonical_model_id":"nvidia/llama-3.3-nemotron-super-49b-v1","display_name":"Nvidia Nemotron Super 49B","type":"chat"},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nvidia Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.05,"output":0.25,"cache_read":0.025},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nvidia Nemotron 3 Super 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"Nvidia Nemotron 3.5 Super VL","description":"NVIDIA’s open-weight 120B model (12B active) for reasoning, coding, tool use, document and GUI understanding, and video understanding. Text, images and video in; text out. Served in NVFP4 with a 262,144-token shared context window. NanoGPT currently limits responses to 16,384 tokens while separate hosted output limits remain unpublished. OpenMDW 1.1 license.","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.15,"output":0.5,"cache_read":0.02},"display_name":"Nvidia Nemotron 3.5 Super VL","type":"chat"},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nvidia Nemotron 3 Ultra 550B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nvidia Nemotron 3 Ultra 550B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3-super-120b-a12b:thinking","name":"Nvidia Nemotron 3 Super 120B Thinking","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.05,"output":0.25,"cache_read":0.025},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nvidia Nemotron 3 Super 120B Thinking","type":"chat"},{"id":"nvidia/nemotron-3-ultra-550b-a55b:thinking","name":"Nvidia Nemotron 3 Ultra 550B Thinking","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nvidia Nemotron 3 Ultra 550B Thinking","type":"chat"},{"id":"nvidia/nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.05,"output":0.15,"cache_read":0.025},"canonical_model_id":"nvidia/nemotron-3.5-content-safety","display_name":"Nemotron 3.5 Content Safety","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","name":"Nvidia Nemotron 70b","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.357,"output":0.408,"cache_read":0.1785},"canonical_model_id":"nvidia/llama-3.1-nemotron-70b-instruct","display_name":"Nvidia Nemotron 70b","type":"chat"},{"id":"nvidia/nemotron-3.5-lightning:thinking","name":"Nvidia Nemotron 3.5 Lightning Thinking","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nvidia Nemotron 3.5 Lightning Thinking","type":"chat"},{"id":"xiaomi/mimo-v2.5-pro:thinking","name":"MiMo V2.5 Pro Thinking","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro Thinking","type":"chat"},{"id":"xiaomi/mimo-v2.6-pro","name":"MiMo V2.6 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo V2.6 Pro","type":"chat"},{"id":"xiaomi/mimo-v2.5","name":"MiMo V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo V2.5","type":"chat"},{"id":"xiaomi/mimo-v2.6-flash-uncensored:thinking","name":"MiMo V2.6 Flash Uncensored Thinking","description":"MiMo V2.6 Flash Uncensored with maximum thinking enabled. Supports a 1M-token context window and tool calling.","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-09-26","last_updated":"2026-09-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.5,"output":1.5,"cache_read":0.1995},"display_name":"MiMo V2.6 Flash Uncensored Thinking","type":"chat"},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","name":"MiMo V2.6 Pro UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.6-pro-ultraspeed","display_name":"MiMo V2.6 Pro UltraSpeed","type":"chat"},{"id":"xiaomi/mimo-v2.5:thinking","name":"MiMo V2.5 Thinking","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo V2.5 Thinking","type":"chat"},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro","type":"chat"},{"id":"xiaomi/mimo-v2.6-flash","name":"MiMo V2.6 Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo V2.6 Flash","type":"chat"},{"id":"xiaomi/mimo-v2.6-flash-abliterated","name":"MiMo V2.6 Flash Abliterated","description":"A MiMo V2.6 Flash finetune with refusal-direction ablation, image input, a 1M-token context window, separate reasoning output, and tool calling.","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-09-25","last_updated":"2026-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.5,"output":1.5,"cache_read":0.275},"display_name":"MiMo V2.6 Flash Abliterated","type":"chat"},{"id":"xiaomi/mimo-v2.6-flash-uncensored","name":"MiMo V2.6 Flash Uncensored","description":"A text-only, lower-refusal MiMo V2.6 Flash finetune served by Heabsy with a 1M-token context window, separate reasoning output, and tool calling.","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-09-25","last_updated":"2026-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.5,"output":1.5,"cache_read":0.1995},"display_name":"MiMo V2.6 Flash Uncensored","type":"chat"},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-06-30","release_date":"2023-07-22","last_updated":"2023-07-22","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":6144,"input":6144,"output":4096},"cost":{"input":0.799,"output":1.207,"cache_read":0.3995},"canonical_model_id":"undi95/remm-slerp-l2-13b","display_name":"ReMM SLERP 13B","type":"chat"},{"id":"Salesforce/Llama-xLAM-2-70b-fc-r","name":"Llama-xLAM-2 70B fc-r","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-04-13","last_updated":"2025-04-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":2.5,"cache_read":1.25},"display_name":"Llama-xLAM-2 70B fc-r","type":"chat"},{"id":"minimax/minimax-latest","name":"MiniMax Latest","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"input":512000,"output":80000},"cost":{"input":0.23,"output":0.96,"cache_read":0.05},"display_name":"MiniMax Latest","type":"chat"},{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.27,"output":1.08,"cache_read":0.027},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-turbo","name":"MiniMax M2.7 Turbo","description":"Efficient MiniMax model for quick assistance, coding, and routine automation","family":"minimax-m2.7","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06},"display_name":"MiniMax M2.7 Turbo","type":"chat"},{"id":"minimax/minimax-01","name":"MiniMax 01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000192,"input":1000192,"output":16384},"cost":{"input":0.1394,"output":1.122,"cache_read":0.0697},"display_name":"MiniMax 01","type":"chat"},{"id":"minimax/minimax-m2-her","name":"MiniMax M2-her","description":"MiniMax M2 variant tuned for conversational and character-driven agent interactions","family":"minimax","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65532,"input":65532,"output":2048},"cost":{"input":0.302,"output":1.207,"cache_read":0.151},"canonical_model_id":"minimax/MiniMax-M2-Her","display_name":"MiniMax M2-her","type":"chat"},{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.21,"output":0.84,"cache_read":0.042},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3:thinking","name":"MiniMax M3 Thinking","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"input":512000,"output":80000},"cost":{"input":0.23,"output":0.96,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3 Thinking","type":"chat"},{"id":"minimax/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"input":512000,"output":80000},"cost":{"input":0.23,"output":0.96,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.33,"output":1.32,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2","name":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.17,"output":1.53,"cache_read":0.085},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax M2","type":"chat"},{"id":"inflatebot/MN-12B-Mag-Mell-R1","name":"Mag Mell R1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Mag Mell R1","type":"chat"},{"id":"soob3123/Veiled-Calla-12B","name":"Veiled Calla 12B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-04-13","last_updated":"2025-04-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"display_name":"Veiled Calla 12B","type":"chat"},{"id":"soob3123/amoral-gemma3-27B-v2","name":"Amoral Gemma3 27B v2","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-05-23","last_updated":"2025-05-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"display_name":"Amoral Gemma3 27B v2","type":"chat"},{"id":"stepfun/step-5-preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":1,"output":2.7,"cache_read":0.05},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"stepfun/step-3.7-flash:thinking","name":"Step 3.7 Flash Thinking","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash Thinking","type":"chat"},{"id":"Sao10K/L3.1-70B-Hanami-x1","name":"Llama 3.1 70B Hanami","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Llama 3.1 70B Hanami","type":"chat"},{"id":"Sao10K/L3.1-70B-Euryale-v2.2","name":"Llama 3.1 70B Euryale","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":20480,"input":20480,"output":16384},"cost":{"input":0.306,"output":0.357,"cache_read":0.153},"display_name":"Llama 3.1 70B Euryale","type":"chat"},{"id":"Sao10K/L3.3-70B-Euryale-v2.3","name":"Llama 3.3 70B Euryale","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":20480,"input":20480,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"Llama 3.3 70B Euryale","type":"chat"},{"id":"Sao10K/L3-8B-Stheno-v3.2","name":"Sao10K Stheno 8b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-11-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"display_name":"Sao10K Stheno 8b","type":"chat"},{"id":"inception/mercury-2.5-preview","name":"Mercury 2.5 Preview","description":"Mercury 2.5 Preview is Inception's latest and most intelligent diffusion language model. Instead of generating tokens strictly one at a time, it produces and refines multiple tokens in parallel, reaching up to 1,107 tokens per second on standard GPUs. It delivers a 10+ point intelligence gain over Mercury 2, with tunable reasoning, parallel tool calls, schema-aligned JSON output, and a 260K context window. It is built for latency-sensitive production work such as search agents, voice pipelines, customer support, rapid coding iteration, and coding subagents.","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":260000,"input":260000,"output":65536},"cost":{"input":0.04,"output":0.15,"cache_read":0.004},"display_name":"Mercury 2.5 Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ornith-ai/ornith-1.5-35b-a3b","name":"Ornith 1.5 35B","description":"Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, tool use, image understanding, and long-context work. This variant disables thinking for faster direct responses.","family":"ornith","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-07-29","last_updated":"2026-08-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"display_name":"Ornith 1.5 35B","type":"chat"},{"id":"ornith-ai/ornith-1.5-35b-a3b:thinking","name":"Ornith 1.5 35B Thinking","description":"Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, reasoning, tool use, image understanding, and long-context work. This variant enables thinking by default.","family":"ornith","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-07-29","last_updated":"2026-08-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"display_name":"Ornith 1.5 35B Thinking","type":"chat"},{"id":"amazon/nova-lite-v1","name":"Amazon Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"input":300000,"output":5120},"cost":{"input":0.0595,"output":0.238,"cache_read":0.02975},"canonical_model_id":"amazon/nova-lite-v1","display_name":"Amazon Nova Lite 1.0","type":"chat"},{"id":"amazon/nova-2-lite-v1","name":"Amazon Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65535},"cost":{"input":0.51,"output":4.25,"cache_read":0.255},"canonical_model_id":"amazon/nova-2-lite-v1","display_name":"Amazon Nova 2 Lite","type":"chat"},{"id":"amazon/nova-pro-v1","name":"Amazon Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"input":300000,"output":32000},"cost":{"input":0.799,"output":3.196,"cache_read":0.3995},"canonical_model_id":"amazon/nova-pro-v1","display_name":"Amazon Nova Pro 1.0","type":"chat"},{"id":"Doctor-Shotgun/MS3.2-24B-Magnum-Diamond","name":"MS3.2 24B Magnum Diamond","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"display_name":"MS3.2 24B Magnum Diamond","type":"chat"},{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.8,"output":1.6,"cache_read":0.2},"canonical_model_id":"aion-labs/aion-2.0","display_name":"AionLabs: Aion-2.0","type":"chat"},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"Llama 3.1 8b (uncensored)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12-31","release_date":"2025-02-04","last_updated":"2025-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.8,"output":1.6,"cache_read":0.4},"canonical_model_id":"aion-labs/aion-rp-llama-3.1-8b","display_name":"Llama 3.1 8b (uncensored)","type":"chat"},{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion 3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":3,"output":6,"cache_read":0.75},"canonical_model_id":"aion-labs/aion-3.0","display_name":"AionLabs: Aion 3.0","type":"chat"},{"id":"aion-labs/aion-3.5","name":"AionLabs: Aion 3.5","description":"A GLM-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":3,"output":6,"cache_read":0.75},"display_name":"AionLabs: Aion 3.5","type":"chat"},{"id":"aion-labs/aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","description":"A GLM-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.7,"output":1.4,"cache_read":0.18},"display_name":"AionLabs: Aion 3.5 Mini","type":"chat"},{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion 3.0 Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.7,"output":1.4,"cache_read":0.18},"canonical_model_id":"aion-labs/aion-3.0-mini","display_name":"AionLabs: Aion 3.0 Mini","type":"chat"},{"id":"qwen/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max:thinking","name":"Qwen3.8 Max Thinking","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"input":991000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max Thinking","type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.3,"output":1.9,"cache_read":0.15},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1001536,"input":1001536,"output":32768},"cost":{"input":0.15,"output":0.7,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-thinking","display_name":"Qwen3 VL 235B A22B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-27b-kiwen","name":"Qwen 3.8 27B Kiwen","description":"Qwen 3.8 27B Kiwen is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Kiwen","type":"chat"},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.25,"output":2,"cache_read":0.135},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-omni-plus","name":"Qwen3.5 Omni Plus","description":"Qwen3.5 Omni Plus is Qwen's stronger general multimodal model. We verified live support for text prompts, images, audio files, and direct video URLs on Alibaba's chat-completions-compatible API. Alibaba describes Plus as a comprehensive evolution of Qwen3 Omni with support for over 10 hours of audio input.","family":"qwen3.5","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"display_name":"Qwen3.5 Omni Plus","type":"chat"},{"id":"qwen/qwen3.7-flash:thinking","name":"Qwen3.7 Flash Thinking","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash Thinking","type":"chat"},{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen 3 235b A22B 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.0875,"output":0.35,"cache_read":0.0175},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen 3 235b A22B 2507","type":"chat"},{"id":"qwen/qwen-max","name":"Qwen 2.5 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":1.5997,"output":6.392,"cache_read":0.79985},"canonical_model_id":"alibaba/qwen-max","display_name":"Qwen 2.5 Max","type":"chat"},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.15,"output":0.65,"cache_read":0.075},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-thinking","display_name":"Qwen3 Next 80B A3B (Thinking)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"input":991000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.250251,"output":0.80293,"cache_read":0.079764},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"qwen/qwen3-coder","name":"Qwen 3 Coder 480B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"input":262000,"output":65536},"cost":{"input":0.13,"output":0.5,"cache_read":0.065},"display_name":"Qwen 3 Coder 480B","type":"chat"},{"id":"qwen/qwen3.5-35b-a3b:thinking","name":"Qwen3.5 35B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.14,"output":1,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B A3B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.4,"output":2.4,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-27b-swift","name":"Qwen 3.8 27B Swift","description":"Qwen 3.8 27B Swift is a finetune for fast responses, served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Swift","type":"chat"},{"id":"qwen/qwen3.8-27b-fimi","name":"Qwen 3.8 27B Fimi","description":"Qwen 3.8 27B Fimi is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Fimi","type":"chat"},{"id":"qwen/qwen3-32b","name":"Qwen 3 32b","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen 3 32b","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-27b-kimiko","name":"Qwen 3.8 27B Kimiko","description":"Qwen 3.8 27B Kimiko is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Kimiko","type":"chat"},{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":995904,"input":995904,"output":32768},"cost":{"input":0.3995,"output":1.2002,"cache_read":0.19975},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.2002,"output":6.001,"cache_read":0.6001},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-27b-obliterated:thinking","name":"Qwen 3.8 27B Obliterated Thinking","description":"Qwen 3.8 27B Obliterated with thinking enabled for more deliberate creative work, coding, multimodal analysis, tool use, and long-context problem solving.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-07-29","last_updated":"2026-08-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.25,"output":1.75,"cache_read":0.225},"display_name":"Qwen 3.8 27B Obliterated Thinking","type":"chat"},{"id":"qwen/qwen3.8-27b-antislop","name":"Qwen 3.8 27B Antislop","description":"Qwen 3.8 27B Antislop is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Antislop","type":"chat"},{"id":"qwen/qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":8192},"cost":{"input":0.04998,"output":0.2006,"cache_read":0.02499},"canonical_model_id":"alibaba/qwen-turbo","display_name":"Qwen Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3 Coder 30B A3B Instruct","type":"chat"},{"id":"qwen/qwen3.8-27b:thinking","name":"Qwen3.8 27B Thinking","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1001536,"input":1001536,"output":32768},"cost":{"input":0.15,"output":0.7,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B Thinking","type":"chat"},{"id":"qwen/qwen3.8-27b-obliterated","name":"Qwen 3.8 27B Obliterated","description":"Qwen 3.8 27B Obliterated is an open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-07-29","last_updated":"2026-08-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.25,"output":1.75,"cache_read":0.225},"display_name":"Qwen 3.8 27B Obliterated","type":"chat"},{"id":"qwen/qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","type":"chat"},{"id":"qwen/qwen3.8-27b-uncensored","name":"Qwen 3.8 27B Uncensored","description":"Qwen 3.8 27B Uncensored is an NVFP4 open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-07-29","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":32768},"cost":{"input":1,"output":3,"cache_read":0.22},"display_name":"Qwen 3.8 27B Uncensored","type":"chat"},{"id":"qwen/qwen3.7-max:thinking","name":"Qwen3.7 Max Thinking","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max Thinking","type":"chat"},{"id":"qwen/qwen3-235b-a22b","name":"Qwen 3 235b A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.0875,"output":0.35,"cache_read":0.0175},"canonical_model_id":"alibaba/qwen3-235b-a22b","display_name":"Qwen 3 235b A22B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.26,"output":2.08,"cache_read":0.103788},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-27b-uncensored:thinking","name":"Qwen 3.8 27B Uncensored Thinking","description":"Qwen 3.8 27B Uncensored with thinking enabled for more deliberate creative work, coding, multimodal analysis, tool use, and long-context problem solving.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-07-29","last_updated":"2026-08-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":32768},"cost":{"input":1,"output":3,"cache_read":0.22},"display_name":"Qwen 3.8 27B Uncensored Thinking","type":"chat"},{"id":"qwen/qwen3.5-omni-flash","name":"Qwen3.5 Omni Flash","description":"Qwen3.5 Omni Flash is Qwen's fast multimodal model. We verified live support for text prompts, images, audio files, and direct video URLs on Alibaba's chat-completions-compatible API. Alibaba describes Flash as a fully evolved version of Qwen3 Omni with audio input support across 60+ languages.","family":"qwen3.5","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":49152,"input":49152,"output":16384},"display_name":"Qwen3.5 Omni Flash","type":"chat"},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.112,"output":0.8,"cache_read":0.056},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B (Instruct)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":1.1,"cache_read":0.07},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3 Next 80B A3B (Instruct)","type":"chat"},{"id":"qwen/qwen3-max-2026-01-23","name":"Qwen3 Max 2026-01-23","description":"Qwen3 Max is Alibaba's flagship Qwen 3 reasoning model with native tool use (web search, web extractor, code interpreter) and a 256K context window.","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"release_date":"2026-01-26","last_updated":"2026-01-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.2002,"output":6.001,"cache_read":0.6001},"display_name":"Qwen3 Max 2026-01-23","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-27b-fable","name":"Qwen 3.8 27B Fable","description":"Qwen 3.8 27B Fable is an open-weight multimodal creative finetune for expressive dialogue, long-form storytelling, character work, and roleplay.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-29","last_updated":"2026-08-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.25,"output":1.5,"cache_read":0.125},"display_name":"Qwen 3.8 27B Fable","type":"chat"},{"id":"qwen/qwen3.8-27b-hemmingway","name":"Qwen 3.8 27B Hemingway","description":"Qwen 3.8 27B Hemingway is an open-weight NVFP4 multimodal creative finetune for long-form prose, character dialogue, storytelling, and roleplay.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.25,"output":1.5,"cache_read":0.125},"display_name":"Qwen 3.8 27B Hemingway","type":"chat"},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.19,"output":1.16,"cache_read":0.02,"cache_write":0.24},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.15},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen/qwen3.5-plus:thinking","name":"Qwen3.5 Plus Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.4,"output":2.4,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-27b-darkidol","name":"Qwen 3.8 27B DarkIdol","description":"Qwen 3.8 27B DarkIdol is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B DarkIdol","type":"chat"},{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.05,"output":0.15,"cache_read":0.025},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-122b-a10b:thinking","name":"Qwen3.5 122B A10B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.26,"output":2.08,"cache_read":0.103788},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B A10B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b:thinking","name":"Qwen3.5 397B A17B Thinking","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.39,"output":2.34,"cache_read":0.3},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B A17B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max-prime","name":"Qwen3.8 Max Prime","description":"High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows","family":"qwen3.8-max","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":4,"output":12,"cache_read":0.5},"canonical_model_id":"alibaba/qwen3.8-max-prime","display_name":"Qwen3.8 Max Prime","type":"chat"},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":131072},"cost":{"input":0.14,"output":0.42,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b-cybersecurity","name":"Qwen 3.8 27B Cybersecurity","description":"Qwen 3.8 27B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-19","last_updated":"2026-09-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Cybersecurity","type":"chat"},{"id":"qwen/qwen3.8-27b-novelist","name":"Qwen 3.8 27B Novelist","description":"Qwen 3.8 27B Novelist is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Novelist","type":"chat"},{"id":"qwen/qwen-long","name":"Qwen Long 10M","description":"Alibaba's huge context window model. Takes in up to 10 million tokens, which is equivalent to dozens of books.","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2024-08-01","last_updated":"2024-08-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":10000000,"input":10000000,"output":8192},"cost":{"input":0.1003,"output":0.408,"cache_read":0.05015},"display_name":"Qwen Long 10M","type":"chat"},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.14,"output":1,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":245760,"input":245760,"output":65536},"cost":{"input":1.04,"output":6.24,"cache_read":0.52},"canonical_model_id":"alibaba/qwen3.6-max-preview","display_name":"Qwen3.6 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3-30b-a3b","display_name":"Qwen3 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.39,"output":2.34,"cache_read":0.3},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-8b","name":"Qwen 3 8B","description":"Qwen 3 8B is a 8B model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.47,"output":0.47,"cache_read":0.235},"display_name":"Qwen 3 8B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-27b:thinking","name":"Qwen3.5 27B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.25,"output":2,"cache_read":0.135},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B Thinking","type":"chat"},{"id":"qwen/qwen3.8-27b-queen","name":"Qwen 3.8 27B Queen","description":"Qwen 3.8 27B Queen is an open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 262,144-token context window.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-09-09","last_updated":"2026-09-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.25,"output":1.5,"cache_read":0.125},"display_name":"Qwen 3.8 27B Queen","type":"chat"},{"id":"qwen/qwen3.8-27b-synthia","name":"Qwen 3.8 27B Synthia","description":"Qwen 3.8 27B Synthia is a text-only roleplay finetune served by Aoru in NVFP4 with a 262,144-token context window.","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"display_name":"Qwen 3.8 27B Synthia","type":"chat"},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.2,"output":0.5,"cache_read":0.1},"display_name":"Qwen3 30B A3B Instruct 2507","type":"chat"},{"id":"qwen/qwen2.5-coder-32b-instruct","name":"Qwen 2.5 Coder 32b","description":"Open coding-focused Qwen model for code generation, repair, and repository reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"canonical_model_id":"alibaba/qwen2.5-coder-32b-instruct","display_name":"Qwen 2.5 Coder 32b","type":"chat"},{"id":"qwen/qwen3.7-plus:thinking","name":"Qwen3.7 Plus Thinking","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus Thinking","type":"chat"},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2025-07-03","last_updated":"2025-07-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.36,"output":0.4,"cache_read":0.1785},"display_name":"Qwen2.5 72B","type":"chat"},{"id":"qwen/qwen3.6-35b-a3b:thinking","name":"Qwen3.6 35B A3B Thinking","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.112,"output":0.8,"cache_read":0.056},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.203,"output":2.24,"cache_read":0.1015},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-plus","name":"Qwen 3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.325,"output":1.95,"cache_read":0.0325,"cache_write":0.40625},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen 3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-27b:thinking","name":"Qwen3.6 27B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.203,"output":2.24,"cache_read":0.1015},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-14b","name":"Qwen 3 14b","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.08,"output":0.24,"cache_read":0.04},"display_name":"Qwen 3 14b","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-flash:thinking","name":"Qwen3.5 Flash Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5","name":"Llama 3 70B abliterated","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"display_name":"Llama 3 70B abliterated","type":"chat"},{"id":"openai/gpt-5.4","name":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT 5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"input":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5 Turbo","type":"chat"},{"id":"openai/gpt-terra-latest","name":"GPT Terra Latest","description":"Compatibility alias that routes to GPT 5.6 Terra, the latest supported GPT Terra model.","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"display_name":"GPT Terra Latest","type":"chat"},{"id":"openai/gpt-6-astra-pro","name":"GPT 6 Astra Pro","description":"GPT 6 Astra in Pro reasoning mode. Uses additional model work for difficult tasks, with higher latency and token usage at the same per-token rates. Reasoning effort remains independently configurable.","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"GPT 6 Astra Pro","type":"chat"},{"id":"openai/o3-pro-2025-06-10","name":"OpenAI o3-pro (2025-06-10)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-06-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":22,"output":88,"cache_read":11},"display_name":"OpenAI o3-pro (2025-06-10)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-nano","name":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT 5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-codex","name":"GPT 5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT 5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex","name":"GPT 5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT 5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-chat-latest","name":"GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"display_name":"GPT Chat Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.6-sol-pro","name":"GPT 5.6 Sol Pro","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT 5.6 Sol Pro","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT 5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT 5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"OpenAI o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o4-mini","display_name":"OpenAI o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"OpenAI o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"OpenAI o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.3-codex","name":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT 5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT 4.1 Nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT 4.1 Nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT 5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT 5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1","name":"OpenAI o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"canonical_model_id":"openai/o1","display_name":"OpenAI o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-latest","name":"GPT Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"GPT Latest","type":"chat"},{"id":"openai/gpt-5-pro","name":"GPT 5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":15,"output":120,"cache_read":1.5},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT 5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT 6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT 6.1 Sol","type":"chat"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-08-06","display_name":"GPT-4o (2024-08-06)","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT 6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT 6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-luna-latest","name":"GPT Luna Latest","description":"Compatibility alias that routes to GPT 5.6 Luna, the latest supported GPT Luna model.","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"display_name":"GPT Luna Latest","type":"chat"},{"id":"openai/gpt-5.6-luna-pro","name":"GPT 5.6 Luna Pro","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT 5.6 Luna Pro","type":"chat"},{"id":"openai/gpt-5.1","name":"GPT 5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.02,"output":0.1},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.075,"output":0.3},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B","type":"chat"},{"id":"openai/o3-mini-high","name":"OpenAI o3-mini (High)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-01-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"OpenAI o3-mini (High)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-sol-latest","name":"GPT Sol Latest","description":"Compatibility alias that routes to GPT 5.6 Sol, the latest supported GPT Sol model.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"display_name":"GPT Sol Latest","type":"chat"},{"id":"openai/gpt-6-sol-pro","name":"GPT 6 Sol Pro","description":"GPT-6 Sol Pro uses the same underlying model as GPT-6 Sol with Pro reasoning mode enabled for higher-quality responses on complex tasks.","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"display_name":"GPT 6 Sol Pro","type":"chat"},{"id":"openai/gpt-astra-latest","name":"GPT Astra Latest","description":"Compatibility alias that routes to GPT 6 Astra, the latest supported GPT Astra model.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"GPT Astra Latest","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT 5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT 5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT 5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-max","name":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":2.5,"output":20,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT 5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT 5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT 5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT 4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT 4.1","type":"chat"},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-11-20","display_name":"GPT-4o (2024-11-20)","type":"chat"},{"id":"openai/o3-mini-low","name":"OpenAI o3-mini (Low)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-01-31","last_updated":"2025-01-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"OpenAI o3-mini (Low)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-mini","name":"GPT 4.1 Mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT 4.1 Mini","type":"chat"},{"id":"openai/gpt-5.6-terra-pro","name":"GPT 5.6 Terra Pro","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT 5.6 Terra Pro","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT 6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT 6 Luna","type":"chat"},{"id":"openai/gpt-6.1-sol-pro","name":"GPT 6.1 Sol Pro","description":"GPT-6.1 Sol Pro uses the same underlying model as GPT-6.1 Sol with Pro reasoning mode enabled for higher-quality responses on complex tasks.","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"display_name":"GPT 6.1 Sol Pro","type":"chat"},{"id":"openai/o4-mini-high","name":"OpenAI o4-mini high","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-12-04","last_updated":"2025-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"OpenAI o4-mini high","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-luna-pro","name":"GPT 6 Luna Pro","description":"GPT-6 Luna Pro uses the same underlying model as GPT-6 Luna with Pro reasoning mode enabled for higher-quality responses on complex tasks.","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"display_name":"GPT 6 Luna Pro","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT 5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT 5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.03,"output":0.15,"cache_read":0.03},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1-codex-mini","name":"GPT 5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT 5.1 Codex Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3","name":"OpenAI o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":1},"canonical_model_id":"openai/o3","display_name":"OpenAI o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT 5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT 5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT 5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-2025-11-13","name":"GPT-5.1 (2025-11-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-11-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1 (2025-11-13)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT 6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT 6 Sol","type":"chat"},{"id":"openai/o1-pro","name":"OpenAI o1 Pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":150,"output":600,"cache_read":75},"canonical_model_id":"openai/o1-pro","display_name":"OpenAI o1 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","description":"Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-04-15","last_updated":"2024-04-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"canonical_model_id":"microsoft/wizardlm-2-8x22b","display_name":"WizardLM-2 8x22B","type":"chat"},{"id":"NousResearch/hermes-3-llama-3.1-70b","name":"Hermes 3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-18","last_updated":"2024-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.408,"output":0.408,"cache_read":0.204},"canonical_model_id":"nousresearch/hermes-3-llama-3.1-70b","display_name":"Hermes 3 70B","type":"chat"},{"id":"NousResearch/hermes-4-405b","name":"Hermes 4 Large","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.15},"canonical_model_id":"nousresearch/hermes-4-405b","display_name":"Hermes 4 Large","type":"chat"},{"id":"NousResearch/hermes-4-405b:thinking","name":"Hermes 4 Large (Thinking)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.15},"canonical_model_id":"nousresearch/hermes-4-405b","display_name":"Hermes 4 Large (Thinking)","type":"chat"},{"id":"ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0","name":"Omega Directive 24B Unslop v2.0","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"display_name":"Omega Directive 24B Unslop v2.0","type":"chat"}]},"abliteration-ai":{"id":"abliteration-ai","api":"https://api.abliteration.ai/v1","name":"abliteration.ai","doc":"https://docs.abliteration.ai/models","display_name":"abliteration.ai","models":[{"id":"abliterated-model-large-v2","name":"Abliterated Model Large V2","description":"GLM-5.3 model abliterated and finetuned for cyber, ML red teaming, and agent testing","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-29","last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":999990},"cost":{"input":5,"output":5,"cache_read":0.5},"display_name":"Abliterated Model Large V2","type":"chat"},{"id":"abliterated-model","name":"Abliterated Model","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-01-06","last_updated":"2026-07-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":150000,"input":150000,"output":8192},"cost":{"input":3,"output":3,"cache_read":0.3},"display_name":"Abliterated Model","type":"chat"},{"id":"abliterated-model-large","name":"Abliterated Model Large","description":"GLM-5.2 model abliterated and finetuned for cyber, ML red teaming, and agent testing","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-25","last_updated":"2026-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":999990},"cost":{"input":5,"output":5,"cache_read":0.5},"display_name":"Abliterated Model Large","type":"chat"}]},"crof":{"id":"crof","api":"https://crof.ai/v1","name":"CrofAI","doc":"https://crof.ai/docs","display_name":"CrofAI","models":[{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.2,"output":1.5,"cache_read":0.03},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"kimi-k3-eco","name":"Kimi K3 Eco","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":1,"output":4,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 Eco","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash","name":"GLM 5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.07,"output":0.22,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash (New)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.08,"output":0.1,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash (New)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":2,"output":8,"cache_read":0.25},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.08,"output":0.2,"cache_read":0.007},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.5,"output":1.99,"cache_read":0.05},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"greg-2-super","name":"Greg 2 Super","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-06-14","last_updated":"2026-06-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":1.5,"output":5,"cache_read":0.25},"display_name":"Greg 2 Super","type":"chat"},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro (0813)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.35,"output":0.8,"cache_read":0.01},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro (0813)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.4,"output":0.8,"cache_read":0.003,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"greg-rp","name":"Greg (Roleplay)","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"display_name":"Greg (Roleplay)","type":"chat"},{"id":"qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-13","last_updated":"2026-03-13","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.04,"output":0.15,"cache_read":0.008},"display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.35,"output":1.75,"cache_read":0.07},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.3,"output":1.05,"cache_read":0.05},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.45,"output":2.15,"cache_read":0.08,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.35,"output":0.8,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.2,"output":1.5,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"greg-2-ultra","name":"Greg 2 Ultra","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-06-14","last_updated":"2026-06-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":3,"output":10,"cache_read":0.5},"display_name":"Greg 2 Ultra","type":"chat"},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":163840},"cost":{"input":0.18,"output":0.35,"cache_read":0.04},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.4,"output":1.4,"cache_read":0.06},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.55,"output":2.25,"cache_read":0.05},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"greg-1-mini","name":"Greg 1 Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":0.07,"output":0.15,"cache_read":0.01},"display_name":"Greg 1 Mini","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.12,"output":0.21,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"standardcompute":{"id":"standardcompute","api":"https://api.stdcmpt.com/v1","name":"Standard Compute","doc":"https://docs.standardcompute.com/models","display_name":"Standard Compute","models":[{"id":"standardcompute","name":"Standard Compute","description":"Flat-rate smart-routing gateway: one model id, each request routed across the customer's enabled models from a curated ~1M-context catalog (Claude, GPT, Gemini, DeepSeek, GLM, Qwen, Kimi, MiniMax, Grok, MiMo) or pinned to a user-selected model","family":"auto","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-10-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"display_name":"Standard Compute","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.14,"output":0.42,"cache_read":0.0042},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":1.122,"output":3.366,"cache_read":0.1122},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":1.044,"output":2.088,"cache_read":0.2088},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.0826,"output":0.1652,"cache_read":0.01652},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.08,"output":0.5,"cache_read":0.012},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.5625,"output":1.8,"cache_read":0.105},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":30000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"mistralai/mistral-large-4-0","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"xiaomi/mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.43,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.425,"output":2.55,"cache_read":0.085,"cache_write":0.53125},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"tiers":[{"input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0.125,"tier":{"type":"context","size":32000}},{"input":0.2,"output":0.8,"cache_read":0.04,"cache_write":0.25,"tier":{"type":"context","size":256000}}]},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4,"tiers":[{"input":0.96,"output":3.84,"cache_read":0.192,"cache_write":1.2,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.96,"output":3.84,"cache_read":0.192,"cache_write":1.2}},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":850000,"output":50000},"provider":{"npm":"@openrouter/ai-sdk-provider"},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}}]},"cloudferro-sherlock":{"id":"cloudferro-sherlock","api":"https://api-sherlock.cloudferro.com/openai/v1/","name":"CloudFerro Sherlock","doc":"https://docs.sherlock.cloudferro.com/","display_name":"CloudFerro Sherlock","models":[{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10-09","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":70000,"output":70000},"cost":{"input":2.92,"output":2.92},"display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196000,"input":180000,"output":16000},"cost":{"input":0.3,"output":1.2},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.34,"output":4.48},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"OpenAI GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":2.92,"output":2.92},"canonical_model_id":"openai/gpt-oss-120b","display_name":"OpenAI GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"speakleash/Bielik-11B-v3.0-Instruct","name":"Bielik 11B v3.0 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.67,"output":0.67},"display_name":"Bielik 11B v3.0 Instruct","type":"chat"}]},"anthropic":{"id":"anthropic","name":"Anthropic","doc":"https://docs.anthropic.com/en/docs/about-claude/models","display_name":"Anthropic","models":[{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":8,"output":40,"cache_read":0.4,"cache_write":10},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-07","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-29","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-04","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-14","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}}]},"tinfoil":{"id":"tinfoil","api":"https://inference.tinfoil.sh/v1","name":"Tinfoil","doc":"https://docs.tinfoil.sh","display_name":"Tinfoil","models":[{"id":"gpt-oss-safeguard-120b","name":"gpt-oss-safeguard-120b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-safeguard-120b","display_name":"gpt-oss-safeguard-120b","type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":4,"output":20,"cache_read":0.8},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama3-3-70b","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":1.75,"output":2.75},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"gemma4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.4,"output":1},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"glm-5-3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.8,"output":5.75,"cache_read":0.45},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"status":"beta","cost":{"input":0.65,"output":1.45,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"nomic-embed-text","name":"Nomic Embed Text v1.5","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2024-02","last_updated":"2024-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":768},"cost":{"input":0.05,"output":0},"display_name":"Nomic Embed Text v1.5","type":"chat"},{"id":"gpt-oss-120b","name":"gpt-oss-120b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"llama":{"id":"llama","api":"https://api.llama.com/compat/v1/","name":"Llama","doc":"https://llama.developer.meta.com/docs/models","display_name":"Llama","models":[{"id":"llama-4-maverick-17b-128e-instruct-fp8","name":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama-4-Maverick-17B-128E-Instruct-FP8","type":"chat"},{"id":"groq-llama-4-maverick-17b-128e-instruct","name":"Groq-Llama-4-Maverick-17B-128E-Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Groq-Llama-4-Maverick-17B-128E-Instruct","type":"chat"},{"id":"llama-4-scout-17b-16e-instruct-fp8","name":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama-4-Scout-17B-16E-Instruct-FP8","type":"chat"},{"id":"cerebras-llama-4-maverick-17b-128e-instruct","name":"Cerebras-Llama-4-Maverick-17B-128E-Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Cerebras-Llama-4-Maverick-17B-128E-Instruct","type":"chat"},{"id":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"llama-3.3-8b-instruct","name":"Llama-3.3-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama-3.3-8B-Instruct","type":"chat"},{"id":"cerebras-llama-4-scout-17b-16e-instruct","name":"Cerebras-Llama-4-Scout-17B-16E-Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Cerebras-Llama-4-Scout-17B-16E-Instruct","type":"chat"}]},"cohere":{"id":"cohere","name":"Cohere","doc":"https://docs.cohere.com/docs/models","display_name":"Cohere","models":[{"id":"command-r-08-2024","name":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"cohere/command-r-08-2024","display_name":"Command R","type":"chat"},{"id":"north-mini-code-1-0","name":"North Mini Code","description":"Cohere coding model for practical software engineering and agentic edits","family":"north","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-09-23","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.cohere.ai/compatibility/v1"},"cost":{"input":0,"output":0},"canonical_model_id":"cohere/north-mini-code-1-0","display_name":"North Mini Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"command-a-translate-08-2025","name":"Command A Translate","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a-translate-08-2025","display_name":"Command A Translate","type":"chat"},{"id":"tiny-aya-fire","name":"Tiny Aya Fire","description":"Compact multilingual model specialized for South Asian languages","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"canonical_model_id":"cohere/tiny-aya-fire","display_name":"Tiny Aya Fire","type":"chat"},{"id":"command-r7b-arabic-02-2025","name":"Command R7B Arabic","description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-02-27","last_updated":"2025-02-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"canonical_model_id":"cohere/command-r7b-arabic-02-2025","display_name":"Command R7B Arabic","type":"chat"},{"id":"tiny-aya-earth","name":"Tiny Aya Earth","description":"Compact multilingual model specialized for West Asian and African languages","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"canonical_model_id":"cohere/tiny-aya-earth","display_name":"Tiny Aya Earth","type":"chat"},{"id":"command-a-plus-05-2026","name":"Command A Plus","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","family":"command-a","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04-01","release_date":"2026-05-20","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a-plus-05-2026","display_name":"Command A Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"command-a-03-2025","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a-03-2025","display_name":"Command A","type":"chat"},{"id":"c4ai-aya-vision-32b","name":"Aya Vision 32B","description":"Open multilingual vision model for OCR, visual reasoning, and image question answering","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-03-04","last_updated":"2025-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4000},"canonical_model_id":"cohere/c4ai-aya-vision-32b","display_name":"Aya Vision 32B","type":"chat"},{"id":"tiny-aya-global","name":"Tiny Aya Global","description":"Compact multilingual model balanced across 70 languages and regions","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"canonical_model_id":"cohere/tiny-aya-global","display_name":"Tiny Aya Global","type":"chat"},{"id":"north-small-translate-09-2026","name":"North Small Translate","description":"Open-weight translation model for more than 50 languages and locale variants","family":"north","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-09-09","last_updated":"2026-09-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16000},"cost":{"input":0,"output":0},"canonical_model_id":"cohere/north-small-translate-1-0","display_name":"North Small Translate","type":"chat"},{"id":"command-r7b-12-2024","name":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"canonical_model_id":"cohere/command-r7b-12-2024","display_name":"Command R7B","type":"chat"},{"id":"command-r-plus-08-2024","name":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-r-plus-08-2024","display_name":"Command R+","type":"chat"},{"id":"command-a-vision-07-2025","name":"Command A Vision","description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","family":"command-a","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a-vision-07-2025","display_name":"Command A Vision","type":"chat"},{"id":"tiny-aya-water","name":"Tiny Aya Water","description":"Compact multilingual model specialized for European and Asia-Pacific languages","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"canonical_model_id":"cohere/tiny-aya-water","display_name":"Tiny Aya Water","type":"chat"},{"id":"command-a-reasoning-08-2025","name":"Command A Reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","family":"command-a","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1}],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a-reasoning-08-2025","display_name":"Command A Reasoning","type":"chat"},{"id":"c4ai-aya-expanse-32b","name":"Aya Expanse 32B","description":"Open multilingual model optimized for generation across 23 languages","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-10-24","last_updated":"2024-10-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"canonical_model_id":"cohere/c4ai-aya-expanse-32b","display_name":"Aya Expanse 32B","type":"chat"}]},"deepseek":{"id":"deepseek","api":"https://api.deepseek.com","name":"DeepSeek","doc":"https://api-docs.deepseek.com/quick_start/pricing","display_name":"DeepSeek","models":[{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental vision-enabled DeepSeek V4 Flash model","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"status":"deprecated","cost":{"input":0.14,"output":0.28,"reasoning":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4 Flash Vision Exp","metadata":{"lifecycle":"preview"},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat","experimental":true,"vision":true},{"id":"deepseek-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model with native multimodal understanding and a 1M-token context window","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"reasoning":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash","metadata":{"lifecycle":"active","pricingBasis":"peak","notes":["USD per million tokens at peak hours; official off-peak prices are half these rates.","Temperature is effective only with thinking disabled; thinking mode ignores sampling parameters."]},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":true},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.66,"output":1.98,"reasoning":1.98,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"status":"deprecated","cost":{"input":0.15,"output":0.6,"reasoning":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"}]},"baseten":{"id":"baseten","api":"https://inference.baseten.co/v1","name":"Baseten","doc":"https://docs.baseten.co/inference/model-apis/overview","display_name":"Baseten","models":[{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.5,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":1,"output":4.05},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-25","last_updated":"2025-08-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":131000},"status":"deprecated","cost":{"input":0.5,"output":1.5},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.13,"output":0.26,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.32,"output":3.96},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","name":"DeepSeek V4.1 Flash Fast","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.6,"output":2.4},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204000,"output":204000},"status":"deprecated","cost":{"input":0.3,"output":1.2},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":3,"output":15},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-01-30","last_updated":"2026-02-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.6,"output":3,"cache_read":0.12},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":1.3,"output":4.3,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.4,"output":4.4,"cache_read":0.3},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-4.7","name":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":200000},"cost":{"input":0.6,"output":2.2,"cache_read":0.12},"display_name":"GLM 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.2-Fast","name":"GLM 5.2 Fast","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":2.1,"output":6.6,"cache_read":0.21},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.3-Fast","name":"GLM 5.3 Fast","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":2.1,"output":6.6},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 Fast","type":"chat"},{"id":"zai-org/GLM-5","name":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":0.95,"output":3.15,"cache_read":0.2},"display_name":"GLM 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3","name":"GLM 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nvidia/Nemotron-120B-A12B","name":"Nemotron Super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":0.3,"output":0.75,"cache_read":0.06},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron Super","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron Ultra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-oss-120b","name":"OpenAI GPT 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128072,"output":128072},"cost":{"input":0.1,"output":0.5},"display_name":"OpenAI GPT 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"nan":{"id":"nan","api":"https://api.nan.builders/v1","name":"NaN","doc":"https://nan.builders/docs/models","display_name":"NaN","models":[{"id":"qwen-image-2.1","name":"Qwen-Image-2.1","description":"Unified text-to-image generation and image editing model with native RGBA transparency and reference-image editing","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-09-14","last_updated":"2026-09-21","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen-image-2.1","display_name":"Qwen-Image-2.1","type":"chat"},{"id":"glm5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat"},{"id":"gemma4","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"qwen3.6","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat"},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"stepfun-ai-step-plan":{"id":"stepfun-ai-step-plan","api":"https://api.stepfun.ai/step_plan/v1","name":"StepFun Step Plan (Global)","doc":"https://platform.stepfun.ai/docs/en/step-plan/integrations/reasoning-api","display_name":"StepFun Step Plan (Global)","models":[{"id":"step-5-preview","name":"Step 5 Preview","description":"StepFun frontier model for large-scale agent applications, coding, and knowledge work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":384000},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","metadata":{"source":"public-provider-conf-template","lifecycle":"preview","notes":["Official maximum input and output are both 1M tokens and max_tokens defaults to INF; 384000 is recorded as a conservative default output ceiling.","Step Plan usage is billed as monthly subscription Credits rather than per-token prices."]},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["low","medium","high"],"mode":"effort","effort":"medium"}},"temperature":true,"type":"chat","vision":true},{"id":"step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"canonical_model_id":"stepfun/step-3.5-flash-2603","display_name":"Step 3.5 Flash 2603","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"}]},"nearai":{"id":"nearai","api":"https://cloud-api.near.ai/v1","name":"NEAR AI Cloud","doc":"https://docs.near.ai/","display_name":"NEAR AI Cloud","models":[{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":1.1,"output":1.1,"cache_read":0.55},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.08,"output":0.5,"cache_read":0.012},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"black-forest-labs/FLUX.2-klein-4B","name":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":1,"output":1},"display_name":"FLUX.2 Klein 4B","type":"chat"},{"id":"x-ai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3-Reranker-0.6B","name":"Qwen3 Reranker 0.6B","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-03","last_updated":"2025-06-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":1024},"cost":{"input":0.01,"output":0.01},"display_name":"Qwen3 Reranker 0.6B","type":"rerank"},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.04,"output":1.35,"cache_read":0.018},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen3-VL 30B-A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":8192},"cost":{"input":0.15,"output":0.55,"cache_read":0.03},"display_name":"Qwen3-VL 30B-A3B Instruct","type":"chat"},{"id":"Qwen/Qwen3-Embedding-0.6B","name":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-03","last_updated":"2025-06-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":1024},"cost":{"input":0.01,"output":0.01},"display_name":"Qwen3 Embedding 0.6B","type":"embedding"},{"id":"Qwen/Qwen3.6-35B-A3B-FP8","name":"Qwen 3.6 35B A3B FP8","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.17,"output":1.1,"cache_read":0.056},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen 3.6 35B A3B FP8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3.3,"output":16.5,"cache_read":0.33},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.81,"output":3.85,"cache_read":0.41},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.8,"output":7.5},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.5,"output":3.3,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/whisper-large-v3","name":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":448},"cost":{"input":0.01,"output":0.01},"display_name":"Whisper Large v3","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"wandb":{"id":"wandb","api":"https://api.inference.wandb.ai/v1","name":"CoreWeave","doc":"https://docs.wandb.ai/inference","display_name":"CoreWeave","models":[{"id":"meta-llama/Llama-3.1-8B-Instruct","name":"Llama 3.1 8B","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.22,"output":0.22,"cache_read":0.22},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama 3.1 8B","type":"chat"},{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.71,"output":0.71,"cache_read":0.71},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B","type":"chat"},{"id":"reflection/Beam-1.0-501B-A23B","name":"Beam 1.0","description":"Beam is a 501B-parameter MoE model with 23B active parameters built for coding, reasoning, and agentic workflows.","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":3,"cache_read":0.1},"display_name":"Beam 1.0","type":"chat"},{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B","description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.34,"cache_read":0.1},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B","type":"chat"},{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B","description":"Gemma 4 26B A4B is a multimodal MoE model with LoRA support and function calling for agentic workflows.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B","type":"chat"},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":3,"cache_read":0.15},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B A3B","description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1.25,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"ibm-granite/granite-4.2-8b","name":"Granite 4.2 8B","description":"Granite 4.2 8B is an instruct model capable of enhanced tool calling, instruction following, and chat capabilities.","family":"granite","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-24","last_updated":"2026-08-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.15,"cache_read":0.05},"display_name":"Granite 4.2 8B","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"A large hybrid model that supports both thinking and non-thinking modes via prompt templates.","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":161000,"output":161000},"cost":{"input":0.55,"output":1.65,"cache_read":0.55},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"DeepSeek V4-Flash-0731 is an MoE model great for coding, reasoning, and agentic workloads.","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.13,"output":0.28,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4-Pro-0813 is a 1.6T-parameter MoE model excelling at advanced reasoning, coding, and complex agentic workloads.","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.31,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a multimodal MoE model for coding, reasoning, and agentic workloads with long contexts.","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.15,"output":0.65,"cache_read":0.002},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax M3","description":"MiniMax M3 is a multimodal MoE model with 23B active parameters optimized for coding and agentic workflows.","family":"minimax-m3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.23,"output":0.96,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi K2.6 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.65,"output":3.41,"cache_read":0.15},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Kimi K2.7 Code is a 1T-parameter MoE model with 32B active parameters purpose-built for long-horizon agentic coding and software engineering.","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.71,"output":3.5,"cache_read":0.15},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.2","name":"GLM 5.2","description":"GLM-5.2 is a Mixture-of-Experts language model featuring 40 billion activated parameters and a total of 744 billion parameters.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.62,"output":2.42,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","description":"GLM-5.3-Flash is a natively multimodal model with 320B total parameters and 18B active parameters.","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.15,"output":0.5,"cache_read":0.02},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.3","name":"GLM 5.3","description":"GLM-5.3 is a 744B-parameter MoE model built for advanced reasoning, software engineering, and long-horizon agentic tasks.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.2,"output":4,"cache_read":0.19},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","name":"Nemotron 3.5 Super VL","description":"Nemotron 3.5 Super VL is a multimodal MoE model built for visual understanding, reasoning, and agentic workflows.","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.15,"output":0.5,"cache_read":0.02},"canonical_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","display_name":"Nemotron 3.5 Super VL","type":"chat"},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","name":"Nemotron 3.5 Lightning","description":"Nemotron 3.5 Lightning is an MoE model built for fast, reliable agentic tasks across use cases such as financial services, cybersecurity, telecom, and retail.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.07,"output":0.2,"cache_read":0.04},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning","type":"chat"},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron 3 Ultra","description":"Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.15,"cache_read":0.1},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra","type":"chat"},{"id":"openai/gpt-oss-20b","name":"gpt-oss-20b","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.13,"cache_read":0.03},"canonical_model_id":"openai/gpt-oss-20b","display_name":"gpt-oss-20b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"gpt-oss-120b","description":"Efficient Mixture-of-Experts model designed for high-reasoning, agentic and general-purpose use cases.","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.17,"cache_read":0.03},"canonical_model_id":"openai/gpt-oss-120b","display_name":"gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"subconscious":{"id":"subconscious","api":"https://api.subconscious.dev/v1","name":"Subconscious","doc":"https://docs.subconscious.dev","display_name":"Subconscious","models":[{"id":"subconscious/deepseek-v4.1-flash-marathon","name":"DeepSeek V4.1 Flash Marathon","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":5000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash Marathon","type":"chat"},{"id":"subconscious/glm-5.3-marathon","name":"GLM-5.3 Marathon","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":5000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 Marathon","type":"chat"}]},"zeldoc":{"id":"zeldoc","api":"https://api.zeldoc.ai/v1","name":"Zeldoc","doc":"https://docs.zeldoc.ai","display_name":"Zeldoc","models":[{"id":"zdev","name":"ZDev","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"display_name":"ZDev","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"databricks":{"id":"databricks","api":"https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1","name":"Databricks","doc":"https://docs.databricks.com/aws/en/machine-learning/foundation-models/","display_name":"Databricks","models":[{"id":"databricks-claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"databricks-gpt-5-6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat"},{"id":"databricks-gemini-3-5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat"},{"id":"databricks-kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat"},{"id":"databricks-glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"databricks-gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"databricks-gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat"},{"id":"databricks-gemini-3-flash","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat"},{"id":"databricks-claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"databricks-gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.2},"display_name":"GPT OSS 20B","type":"chat"},{"id":"databricks-gpt-5-4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat"},{"id":"databricks-gemini-3-pro","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3-pro-preview","display_name":"Gemini 3 Pro Preview","type":"chat"},{"id":"databricks-gpt-5-2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat"},{"id":"databricks-claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"databricks-gemini-3-1-pro","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat"},{"id":"databricks-claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"databricks-gpt-5-6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat"},{"id":"databricks-claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude Opus 4.1 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"databricks-gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.072,"output":0.28},"display_name":"GPT OSS 120B","type":"chat"},{"id":"databricks-gemini-2-5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat"},{"id":"databricks-gemini-2-5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat"},{"id":"databricks-claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"databricks-gpt-5-4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat"},{"id":"databricks-gpt-5-4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat"},{"id":"databricks-claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"databricks-gpt-5-6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"tiers":[{"input":2,"output":9,"cache_read":0.2,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat"},{"id":"databricks-claude-sonnet-4","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"databricks-gpt-5-1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat"},{"id":"databricks-gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat"},{"id":"databricks-gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat"},{"id":"databricks-gpt-5-5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat"}]},"umans-ai-coding-plan":{"id":"umans-ai-coding-plan","api":"https://api.code.umans.ai/v1","name":"Umans AI Coding Plan","doc":"https://app.umans.ai/offers/code/docs","display_name":"Umans AI Coding Plan","models":[{"id":"umans-deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-glm-5.3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131071},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-flash","name":"Umans Flash","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Umans Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131071},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-coder","name":"Umans Coder","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131071},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"Umans Coder","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"kuae-cloud-coding-plan":{"id":"kuae-cloud-coding-plan","api":"https://coding-plan-endpoint.kuaecloud.net/v1","name":"KUAE Cloud Coding Plan","doc":"https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/","display_name":"KUAE Cloud Coding Plan","models":[{"id":"GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"umans-ai":{"id":"umans-ai","api":"https://api.code.umans.ai/v1","name":"Umans AI","doc":"https://app.umans.ai/offers/code/docs/orgs","display_name":"Umans AI","models":[{"id":"umans-deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":0.15,"output":0.6,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-glm-5.3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131071},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-flash","name":"Umans Flash","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":1,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Umans Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131071},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"umans-coder","name":"Umans Coder","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131071},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"Umans Coder","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"siliconflow-com":{"id":"siliconflow-com","api":"https://api.siliconflow.com/v1","name":"SiliconFlow","doc":"https://cloud.siliconflow.com/models","display_name":"SiliconFlow","models":[{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":99560},"cost":{"input":0.21,"output":0.57},"display_name":"ByteDance-Seed/Seed-OSS-36B-Instruct","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nex-agi/Nex-N2-Pro","name":"Nex-N2-Pro","description":"Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"canonical_model_id":"nex-agi/nex-n2-pro","display_name":"Nex-N2-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"tencent/Hunyuan-A13B-Instruct","name":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":117964},"cost":{"input":0.14,"output":0.57},"display_name":"tencent/Hunyuan-A13B-Instruct","type":"chat"},{"id":"tencent/Hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":99615},"cost":{"input":0.132,"output":0.528,"cache_read":0.033},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meituan-longcat/LongCat-2.0","name":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1049000,"output":131072},"cost":{"input":0.75,"output":2.95,"cache_read":0.015},"canonical_model_id":"meituan/longcat-2.0","display_name":"LongCat-2.0","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"google/gemma-4-12B-it","name":"Gemma 4 12B IT","description":"Compact Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":99615},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"google/gemma-4-12b-it","display_name":"Gemma 4 12B IT","type":"chat"},{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":99615},"cost":{"input":0.13,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":99615},"cost":{"input":0.12,"output":0.4},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.29,"output":1},"display_name":"Qwen/Qwen3-VL-30B-A3B-Instruct","type":"chat"},{"id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.18,"output":0.68},"display_name":"Qwen/Qwen3-VL-8B-Instruct","type":"chat"},{"id":"Qwen/Qwen3-VL-32B-Thinking","name":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.2,"output":1.5},"display_name":"Qwen/Qwen3-VL-32B-Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.09,"output":0.3},"display_name":"Qwen/Qwen3-30B-A3B-Instruct-2507","type":"chat"},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.25,"output":2},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":1.6},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-14B","name":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"cost":{"input":0.07,"output":0.28},"display_name":"Qwen/Qwen3-14B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","name":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.29,"output":1},"display_name":"Qwen/Qwen3-VL-30B-A3B-Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-8B","name":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"cost":{"input":0.06,"output":0.06},"display_name":"Qwen/Qwen3-8B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.59,"output":0.59},"display_name":"Qwen/Qwen2.5-72B-Instruct","type":"chat"},{"id":"Qwen/Qwen3-32B","name":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"cost":{"input":0.14,"output":0.57},"display_name":"Qwen/Qwen3-32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-01","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":65536},"cost":{"input":0.07,"output":0.28},"display_name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","type":"chat"},{"id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.05,"output":0.05},"display_name":"Qwen/Qwen2.5-7B-Instruct","type":"chat"},{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.24,"output":1.8},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.26,"output":2.08},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-9B","name":"Qwen/Qwen3.5-9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.15},"display_name":"Qwen/Qwen3.5-9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.39,"output":2.34},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":131000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3-VL-32B-Instruct","name":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.2,"output":0.6},"display_name":"Qwen/Qwen3-VL-32B-Instruct","type":"chat"},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-31","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":65536},"cost":{"input":0.25,"output":1},"display_name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","type":"chat"},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.3,"output":3.2},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3.1","name":"deepseek-ai/DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-25","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.27,"output":1},"display_name":"deepseek-ai/DeepSeek-V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-R1","name":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.5,"output":2.18},"display_name":"deepseek-ai/DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.13,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.50162,"output":3.135,"cache_read":0.135},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V3.2","name":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":65536},"cost":{"input":0.27,"output":0.42,"cache_read":0.135},"display_name":"deepseek-ai/DeepSeek-V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V3","name":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.25,"output":1},"display_name":"deepseek-ai/DeepSeek-V3","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.27,"output":1},"display_name":"deepseek-ai/DeepSeek-V3.1-Terminus","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"deepseek-ai/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-10","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":65536},"cost":{"input":0.27,"output":0.41},"display_name":"deepseek-ai/DeepSeek-V3.2-Exp","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"stepfun-ai/Step-3.5-Flash","name":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","family":"step","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":256000},"cost":{"input":0.1,"output":0.3},"display_name":"stepfun-ai/Step-3.5-Flash","type":"chat"},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMaxAI/MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":197000,"output":131000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"display_name":"MiniMaxAI/MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionAI/Ling-flash-2.0","name":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":49780},"cost":{"input":0.14,"output":0.57},"display_name":"inclusionAI/Ling-flash-2.0","type":"chat"},{"id":"moonshotai/Kimi-K2.6","name":"moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":99560},"cost":{"input":0.77,"output":3.4,"cache_read":0.14},"display_name":"moonshotai/Kimi-K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262000},"cost":{"input":2.7,"output":13.5,"cache_read":0.27},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":99615},"cost":{"input":0.85916,"output":3.8,"cache_read":0.17993},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.5","name":"moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":99560},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"display_name":"moonshotai/Kimi-K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.1","name":"zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":131000},"cost":{"input":1.19,"output":3.74,"cache_read":0.6,"cache_write":0},"display_name":"zai-org/GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":262000},"cost":{"input":1.302,"output":4.092,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-4.5-Air","name":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":98304},"cost":{"input":0.14,"output":0.86},"display_name":"zai-org/GLM-4.5-Air","type":"chat"},{"id":"zai-org/GLM-5","name":"zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":131072},"cost":{"input":0.95,"output":2.55,"cache_read":0.2},"display_name":"zai-org/GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":262000},"cost":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5V-Turbo","name":"zai-org/GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"display_name":"zai-org/GLM-5V-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":262000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-oss-20b","name":"openai/gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":8000},"cost":{"input":0.04,"output":0.18},"display_name":"openai/gpt-oss-20b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"openai/gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":8000},"cost":{"input":0.05,"output":0.45},"display_name":"openai/gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"minimax-coding-plan":{"id":"minimax-coding-plan","api":"https://api.minimax.io/anthropic/v1","name":"MiniMax Token Plan (minimax.io)","doc":"https://platform.minimax.io/docs/token-plan/intro","display_name":"MiniMax Token Plan (minimax.io)","models":[{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M3.1-Flash-Preview","name":"MiniMax-M3.1-Flash-Preview","description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-27","last_updated":"2026-09-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":512000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"minimax/MiniMax-M3.1-Flash-Preview","display_name":"MiniMax-M3.1-Flash-Preview","type":"chat"},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0},"display_name":"MiniMax-M2","type":"chat"},{"id":"MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.5-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"alibaba-coding-plan":{"id":"alibaba-coding-plan","api":"https://coding-intl.dashscope.aliyuncs.com/v1","name":"Alibaba Coding Plan","doc":"https://www.alibabacloud.com/help/en/model-studio/coding-plan","display_name":"Alibaba Coding Plan","models":[{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3 Coder Next","type":"chat"},{"id":"qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-max-2026-01-23","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"input":196601,"output":24576},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"lilac":{"id":"lilac","api":"https://api.getlilac.com/v1","name":"Lilac","doc":"https://docs.getlilac.com/inference/models","display_name":"Lilac","models":[{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":262100},"cost":{"input":0.11,"output":0.35},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimaxai/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax-m3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.28,"output":1.1,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.7,"output":3.5,"cache_read":0.2},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":524288},"cost":{"input":0.9,"output":3,"cache_read":0.27},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"moonshot":{"id":"moonshot","api":"https://api.moonshot.cn/v1","name":"Moonshot AI (China)","doc":"https://platform.moonshot.cn/docs/api/chat","display_name":"Moonshot AI (China)","models":[{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2.7-code","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}},"type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"Kimi K2.6","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2.7-code-highspeed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code Highspeed","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}},"type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"}]},"bothub":{"id":"bothub","api":"https://openai.bothub.ru/v1","name":"Bothub","doc":"https://bothub.ru/models","display_name":"Bothub","models":[{"id":"gemma-4-31b-it:free","name":"Gemma 4 31B IT (free)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT (free)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.12,"output":0.44},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.1,"output":0.28},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"nemotron-3-ultra-550b-a55b:free","name":"Nemotron 3 Ultra (free)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra (free)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.61,"output":4.84},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.06,"output":0.37},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden","interleaved":true}}},{"id":"muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.1,"output":0.2},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3 Contributor","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.72,"output":5.41},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}}]},"xiaomi-token-plan-cn":{"id":"xiaomi-token-plan-cn","api":"https://token-plan-cn.xiaomimimo.com/v1","name":"Xiaomi Token Plan (China)","doc":"https://platform.xiaomimimo.com/#/docs","display_name":"Xiaomi Token Plan (China)","models":[{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS-VoiceDesign","type":"chat"},{"id":"mimo-v2.5-tts","name":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS","type":"chat"},{"id":"mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2-pro","display_name":"MiMo-V2-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2-tts","name":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2-TTS","type":"chat"},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS-VoiceClone","type":"chat"}]},"privatemode-ai":{"id":"privatemode-ai","api":"http://localhost:8080/v1","name":"Privatemode AI","doc":"https://docs.privatemode.ai/api/overview","display_name":"Privatemode AI","models":[{"id":"glm-flash-latest","name":"GLM Flash (latest)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"status":"beta","cost":{"input":0.2311,"output":0.7511,"cache_read":0.0578},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM Flash (latest)","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"status":"beta","cost":{"input":0.2311,"output":0.7511,"cache_read":0.0578},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"whisper-large-v3","name":"Whisper large-v3","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":4096},"cost":{"input":0.01618,"output":0},"canonical_model_id":"openai/whisper-large-v3","display_name":"Whisper large-v3","type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":262144},"status":"deprecated","cost":{"input":1.791,"output":8.9436,"cache_read":0.1733},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ocr-2","name":"DeepSeek OCR 2","description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"status":"beta","cost":{"input":0.8897,"output":1.4675,"cache_read":0.0924},"canonical_model_id":"deepseek/deepseek-ocr-2","display_name":"DeepSeek OCR 2","type":"chat"},{"id":"qwen3-embedding-4b","name":"Qwen3-Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-06","last_updated":"2025-06-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":2560},"cost":{"input":0.1502,"output":0},"display_name":"Qwen3-Embedding 4B","type":"embedding"},{"id":"voxtral-mini-3b","name":"Voxtral Mini 3B","description":"Speech-to-text model for audio transcription, translation, and audio understanding","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07","last_updated":"2025-07","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.00462,"output":0},"display_name":"Voxtral Mini 3B","type":"chat"},{"id":"kimi-latest","name":"Kimi (latest)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":262144},"status":"deprecated","cost":{"input":1.791,"output":8.9436,"cache_read":0.1733},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi (latest)","type":"chat"},{"id":"gpt-oss-120b","name":"gpt-oss-120b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.2311,"output":0.7511,"cache_read":0.0462},"canonical_model_id":"openai/gpt-oss-120b","display_name":"gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"status":"beta","cost":{"input":1.791,"output":6.6326,"cache_read":0.1733},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-latest","name":"GLM (latest)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"status":"beta","cost":{"input":1.791,"output":6.6326,"cache_read":0.1733},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM (latest)","type":"chat"}]},"llmgateway-providers":{"id":"llmgateway-providers","api":"https://api.llmgateway.io/v1","name":"LLM Gateway","doc":"https://llmgateway.io/docs","display_name":"LLM Gateway","models":[{"id":"entrim/glm-5.3-flash","name":"GLM-5.3 Flash (entrim)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.35,"cache_read":0.0175},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (entrim)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"entrim/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (entrim)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.2,"output":0.6,"cache_read":0.005},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (entrim)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"entrim/glm-5.3","name":"GLM-5.3 (entrim)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.5,"output":2,"cache_read":0.15},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (entrim)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"consensusprotocol/gemma-4-31b-it","name":"Gemma 4 31B IT (Consensus Protocol)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.25,"cache_read":0.01},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT (Consensus Protocol)","type":"chat"},{"id":"consensusprotocol/Qwen3.8-27B","name":"Qwen3.8 27B (Consensus Protocol)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.08,"output":0.35,"cache_read":0.05},"display_name":"Qwen3.8 27B (Consensus Protocol)","type":"chat"},{"id":"consensusprotocol/glm-5.3-flash","name":"GLM-5.3 Flash (Consensus Protocol)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.25,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (Consensus Protocol)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"consensusprotocol/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Consensus Protocol)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.55,"cache_read":0.005},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Consensus Protocol)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"consensusprotocol/gpt-oss-20b","name":"GPT OSS 20B (Consensus Protocol)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.04,"output":0.19,"cache_read":0.01},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Consensus Protocol)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"consensusprotocol/mimo-v2.6-flash","name":"MiMo V2.6 Flash (Consensus Protocol)","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.12,"output":0.25,"cache_read":0.0025},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo V2.6 Flash (Consensus Protocol)","type":"chat"},{"id":"consensusprotocol/minimax-m3","name":"MiniMax M3 (Consensus Protocol)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.28,"output":1.1,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3 (Consensus Protocol)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"consensusprotocol/deepseek-v4-flash","name":"DeepSeek V4 Flash (Consensus Protocol)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.1,"output":0.2,"cache_read":0.005},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Consensus Protocol)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepinfra/mimo-v2.6-pro","name":"MiMo V2.6 Pro (DeepInfra)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo V2.6 Pro (DeepInfra)","type":"chat"},{"id":"deepinfra/gemma-4-31b-it","name":"Gemma 4 31B IT (DeepInfra)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT (DeepInfra)","type":"chat"},{"id":"deepinfra/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct (DeepInfra)","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct (DeepInfra)","type":"chat"},{"id":"deepinfra/muse-glimmer-30b","name":"Muse Glimmer 30B (DeepInfra)","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.3,"output":1.2,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B (DeepInfra)","type":"chat"},{"id":"deepinfra/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (DeepInfra)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.2,"output":0.6,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (DeepInfra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash (DeepInfra)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"display_name":"InclusionAI Ling 3.0 Flash (DeepInfra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct (DeepInfra)","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":0.6},"display_name":"Qwen3 VL 30B A3B Instruct (DeepInfra)","type":"chat"},{"id":"deepinfra/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT (DeepInfra)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.07,"output":0.34},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT (DeepInfra)","type":"chat"},{"id":"deepinfra/ling-3.0-flash-vl","name":"Ling 3.0 Flash VL (DeepInfra)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"display_name":"Ling 3.0 Flash VL (DeepInfra)","type":"chat"},{"id":"deepinfra/granite-4.2-8b","name":"Granite 4.2 8B (DeepInfra)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"granite","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":117964},"cost":{"input":0.06,"output":0.25,"cache_read":0.015},"display_name":"Granite 4.2 8B (DeepInfra)","type":"chat"},{"id":"deepinfra/nemotron-3-ultra-550b","name":"Nemotron 3 Ultra 550B (DeepInfra)","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.2,"cache_read":0.1},"display_name":"Nemotron 3 Ultra 550B (DeepInfra)","type":"chat"},{"id":"deepinfra/qwen3.5-9b","name":"Qwen3.5 9B (DeepInfra)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.15},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B (DeepInfra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepinfra/inkling","name":"Inkling (DeepInfra)","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":262144},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling (DeepInfra)","type":"chat"},{"id":"deepinfra/mimo-v2.6-flash","name":"MiMo V2.6 Flash (DeepInfra)","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo V2.6 Flash (DeepInfra)","type":"chat"},{"id":"deepinfra/deepseek-v4-pro","name":"DeepSeek V4 Pro (DeepInfra)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (DeepInfra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepinfra/deepseek-v3.2","name":"DeepSeek V3.2 (DeepInfra)","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":65536},"cost":{"input":0.26,"output":0.38,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2 (DeepInfra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/deepseek-v4-flash","name":"DeepSeek V4 Flash (DeepInfra)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.08,"output":0.18,"cache_read":0.016},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (DeepInfra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"cerebras/gemma-4-31b-it","name":"Gemma 4 31B IT (Cerebras)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.99,"output":1.49},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT (Cerebras)","type":"chat"},{"id":"cerebras/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507 (Cerebras)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":8192},"cost":{"input":0.6,"output":1.2},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B A22B Instruct 2507 (Cerebras)","type":"chat"},{"id":"cerebras/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct (Cerebras)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.85,"output":1.2},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct (Cerebras)","type":"chat"},{"id":"cerebras/glm-4.7","name":"GLM-4.7 (Cerebras)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":2.25,"output":2.75},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7 (Cerebras)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B (Cerebras)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.35,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Cerebras)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/gpt-oss-20b","name":"GPT OSS 20B (Groq)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32766},"cost":{"input":0.1,"output":0.5},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Groq)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/gpt-oss-120b","name":"GPT OSS 120B (Groq)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32766},"cost":{"input":0.15,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Groq)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scx-ai-gp/glm-5.3-flash","name":"GLM-5.3 Flash (SCX.ai)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.088,"output":0.25,"cache_read":0.025},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (SCX.ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scx-ai-gp/glm-5.2-fast","name":"GLM-5.2 Turbo (SCX.ai)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2.156,"output":6.776,"cache_read":0.429},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Turbo (SCX.ai)","type":"chat"},{"id":"scx-ai-gp/qwen3.8-max","name":"Qwen3.8 Max (SCX.ai)","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.54,"output":4.631,"cache_read":0.198,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max (SCX.ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scx-ai-gp/kimi-k3","name":"Kimi K3 (SCX.ai)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3.135,"output":15.675,"cache_read":0.319},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (SCX.ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scx-ai-gp/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (SCX.ai)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.01},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (SCX.ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scx-ai-gp/glm-5.2","name":"GLM-5.2 (SCX.ai)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.605,"output":2.123,"cache_read":0.154},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (SCX.ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"scx-ai-gp/glm-5.3","name":"GLM-5.3 (SCX.ai)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.924,"output":2.904,"cache_read":0.1716},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (SCX.ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scx-ai-gp/kimi-k2.7-code","name":"Kimi K2.7 Code (SCX.ai)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.737,"output":3.08,"cache_read":0.143},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code (SCX.ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"scx-ai-gp/glm-5.3-fast","name":"GLM 5.3 Fast (SCX.ai)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":2.8,"output":8.8,"cache_read":0.56},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 Fast (SCX.ai)","type":"chat"},{"id":"zai/glm-4.6v","name":"GLM-4.6V (Z AI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16000},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM-4.6V (Z AI)","type":"chat"},{"id":"zai/glm-4.5","name":"GLM-4.5 (Z AI)","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5 (Z AI)","type":"chat"},{"id":"zai/glm-5.3-flash","name":"GLM-5.3 Flash (Z AI)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (Z AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.6","name":"GLM-4.6 (Z AI)","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6 (Z AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.5-x","name":"GLM-4.5 X (Z AI)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":2.2,"output":8.9,"cache_read":0.45},"display_name":"GLM-4.5 X (Z AI)","type":"chat"},{"id":"zai/glm-5","name":"GLM-5 (Z AI)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131100},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5 (Z AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-4.5-airx","name":"GLM-4.5 AirX (Z AI)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":1.1,"output":4.5,"cache_read":0.22},"display_name":"GLM-4.5 AirX (Z AI)","type":"chat"},{"id":"zai/glm-4.5v","name":"GLM-4.5V (Z AI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM-4.5V (Z AI)","type":"chat"},{"id":"zai/glm-4-32b-0414-128k","name":"GLM-4 32B (0414-128k) (Z AI)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.1,"output":0.1},"display_name":"GLM-4 32B (0414-128k) (Z AI)","type":"chat"},{"id":"zai/glm-4.6v-flashx","name":"GLM-4.6V FlashX (Z AI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.04,"output":0.4,"cache_read":0.004},"display_name":"GLM-4.6V FlashX (Z AI)","type":"chat"},{"id":"zai/glm-4.7","name":"GLM-4.7 (Z AI)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7 (Z AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-5.2","name":"GLM-5.2 (Z AI)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (Z AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai/glm-5.1","name":"GLM-5.1 (Z AI)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1 (Z AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai/glm-4.7-flashx","name":"GLM-4.7 FlashX (Z AI)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flashx","display_name":"GLM-4.7 FlashX (Z AI)","type":"chat"},{"id":"zai/glm-4.5-air","name":"GLM-4.5 Air (Z AI)","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5 Air (Z AI)","type":"chat"},{"id":"zai/glm-5.3","name":"GLM-5.3 (Z AI)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Z AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"luminal/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (luminal)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.135,"output":0.54,"cache_read":0.0027},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (luminal)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"aws-bedrock/claude-haiku-4-5","name":"Claude Haiku 4.5 (AWS Bedrock)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"aws-bedrock/kimi-k3","name":"Kimi K3 (AWS Bedrock)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"aws-bedrock/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct (AWS Bedrock)","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"cost":{"input":0.24,"output":0.97},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (AWS Bedrock)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"aws-bedrock/claude-opus-5-5","name":"Claude Opus 5.5 (AWS Bedrock)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/claude-fable-5-1","name":"Claude Fable 5.1 (AWS Bedrock)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"aws-bedrock/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct (AWS Bedrock)","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"cost":{"input":0.17,"output":0.66},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B Instruct (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/claude-opus-4-1-20250805","name":"Claude Opus 4.1 (AWS Bedrock)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"aws-bedrock/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (AWS Bedrock)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"aws-bedrock/claude-opus-5","name":"Claude Opus 5 (AWS Bedrock)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"aws-bedrock/claude-fable-5","name":"Claude Fable 5 (AWS Bedrock)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"aws-bedrock/claude-opus-4-8","name":"Claude Opus 4.8 (AWS Bedrock)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"aws-bedrock/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5 (2025-09-29) (AWS Bedrock)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (2025-09-29) (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"aws-bedrock/claude-sonnet-5","name":"Claude Sonnet 5 (AWS Bedrock)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"aws-bedrock/claude-opus-4-6","name":"Claude Opus 4.6 (AWS Bedrock)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"aws-bedrock/grok-4-3","name":"Grok 4.3 (AWS Bedrock)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.3 (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5 (2025-10-01) (AWS Bedrock)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (2025-10-01) (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"aws-bedrock/grok-4-6","name":"Grok 4.6 (AWS Bedrock)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6 (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/claude-haiku-5-5","name":"Claude Haiku 5.5 (AWS Bedrock)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/claude-sonnet-4-6","name":"Claude Sonnet 4.6 (AWS Bedrock)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"aws-bedrock/claude-sonnet-5-5","name":"Claude Sonnet 5.5 (AWS Bedrock)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/grok-4-7","name":"Grok 4.7 (AWS Bedrock)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":524288},"cost":{"input":2,"output":6,"cache_read":0.5},"display_name":"Grok 4.7 (AWS Bedrock)","type":"chat"},{"id":"aws-bedrock/claude-opus-4-7","name":"Claude Opus 4.7 (AWS Bedrock)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (AWS Bedrock)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"aws-bedrock/llama-3.1-70b-instruct","name":"Llama 3.1 70B Instruct (AWS Bedrock)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":2048},"cost":{"input":0.72,"output":0.72},"display_name":"Llama 3.1 70B Instruct (AWS Bedrock)","type":"chat"},{"id":"google-ai-studio/gemini-3.6-flash","name":"Gemini 3.6 Flash (Google AI Studio)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash (Google AI Studio)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-ai-studio/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite (Google AI Studio)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite (Google AI Studio)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google-ai-studio/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview) (Google AI Studio)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro (Preview) (Google AI Studio)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-ai-studio/gemini-3-flash-preview","name":"Gemini 3 Flash (Preview) (Google AI Studio)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash (Preview) (Google AI Studio)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-ai-studio/gemini-pro-latest","name":"Gemini Pro Latest (Google AI Studio)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-27","last_updated":"2026-02-27","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"display_name":"Gemini Pro Latest (Google AI Studio)","type":"chat"},{"id":"google-ai-studio/gemini-3.8-flash","name":"Gemini 3.8 Flash (Google AI Studio)","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash (Google AI Studio)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-ai-studio/gemini-4-argon","name":"Gemini 4 Argon (Google AI Studio)","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":0.375},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon (Google AI Studio)","type":"chat"},{"id":"google-ai-studio/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite (Google AI Studio)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite (Google AI Studio)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (Anthropic)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (Anthropic)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5-5","name":"Claude Opus 5.5 (Anthropic)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (Anthropic)","type":"chat"},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1 (Anthropic)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (Anthropic)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5 (Anthropic)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5 (Anthropic)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8 (Anthropic)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5 (2025-09-29) (Anthropic)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (2025-09-29) (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5 (Anthropic)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6 (Anthropic)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5 (2025-10-01) (Anthropic)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (2025-10-01) (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-haiku-5-5","name":"Claude Haiku 5.5 (Anthropic)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (Anthropic)","type":"chat"},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6 (Anthropic)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5 (Anthropic)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 (Anthropic)","type":"chat"},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7 (Anthropic)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (DeepSeek)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":393216},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (DeepSeek)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro (DeepSeek)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":393216},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (DeepSeek)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017 (DeepSeek)","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":393216},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"display_name":"DeepSeek V4.1 Flash 1017 (DeepSeek)","type":"chat"},{"id":"runpod/kimi-k3","name":"Kimi K3 (Runpod)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Runpod)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"runware/gemma-4-31b-it","name":"Gemma 4 31B IT (Runware)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.102,"output":0.297,"cache_read":0.012},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT (Runware)","type":"chat"},{"id":"runware/glm-5.3-flash","name":"GLM-5.3 Flash (Runware)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"runware/kimi-k3","name":"Kimi K3 (Runware)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"runware/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Runware)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.01},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"runware/kimi-k2.6","name":"Kimi K2.6 (Runware)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.6,"output":3.05,"cache_read":0.13},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"runware/glm-5.2","name":"GLM-5.2 (Runware)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":128000},"cost":{"input":0.8,"output":2.55,"cache_read":0.16},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"runware/deepseek-v4-pro","name":"DeepSeek V4 Pro (Runware)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.961,"output":1.922,"cache_read":0.079},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"runware/gpt-oss-120b","name":"GPT OSS 120B (Runware)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.032,"output":0.14,"cache_read":0.032},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"runware/glm-5.3","name":"GLM-5.3 (Runware)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"runware/deepseek-v4-flash","name":"DeepSeek V4 Flash (Runware)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.076,"output":0.153,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Runware)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"tencent/glm-5v-turbo","name":"GLM-5V Turbo (Tencent Cloud)","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM-5V Turbo (Tencent Cloud)","type":"chat"},{"id":"tencent/kimi-k3","name":"Kimi K3 (Tencent Cloud)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/glm-5","name":"GLM-5 (Tencent Cloud)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"tencent/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed (Tencent Cloud)","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"tencent/kimi-k2.6","name":"Kimi K2.6 (Tencent Cloud)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.858,"output":3.566,"cache_read":0.145},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"tencent/minimax-m2.7","name":"MiniMax M2.7 (Tencent Cloud)","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"tencent/mimo-v2.5-pro","name":"MiMo V2.5 Pro (Tencent Cloud)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"tencent/minimax-m3","name":"MiniMax M3 (Tencent Cloud)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/glm-5.2","name":"GLM-5.2 (Tencent Cloud)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"tencent/hy3","name":"Hy3 (Tencent Cloud)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.132,"output":0.528,"cache_read":0.033},"canonical_model_id":"tencent/hy3","display_name":"Hy3 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy-mt2-plus","name":"Hy-MT2 Plus (Tencent Cloud)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.074,"output":0.295},"display_name":"Hy-MT2 Plus (Tencent Cloud)","type":"chat"},{"id":"tencent/glm-5.1","name":"GLM-5.1 (Tencent Cloud)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1 (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"tencent/glm-5-turbo","name":"GLM-5 Turbo (Tencent Cloud)","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5 Turbo (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/deepseek-v4-pro","name":"DeepSeek V4 Pro (Tencent Cloud)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.435,"output":0.87,"cache_read":0.00363},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"tencent/hy4-preview","name":"Hy4 Preview (Tencent Cloud)","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 Preview (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/kimi-k2.7-code","name":"Kimi K2.7 Code (Tencent Cloud)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"tencent/deepseek-v4-flash","name":"DeepSeek V4 Flash (Tencent Cloud)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Tencent Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"meta-contributor/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor (Meta Contributor)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.2 Contributor (Meta Contributor)","type":"chat"},{"id":"meta-contributor/muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor (Meta Contributor)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.3 Contributor (Meta Contributor)","type":"chat"},{"id":"novita/glm-4.6v","name":"GLM-4.6V (NovitaAI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16000},"cost":{"input":0.3,"output":0.9,"cache_read":0.055},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM-4.6V (NovitaAI)","type":"chat"},{"id":"novita/gemma-4-31b-it","name":"Gemma 4 31B IT (NovitaAI)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT (NovitaAI)","type":"chat"},{"id":"novita/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct (NovitaAI)","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":1.5},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct (NovitaAI)","type":"chat"},{"id":"novita/qwen3.7-max","name":"Qwen3.7 Max (NovitaAI)","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/mimo-v2.5","name":"MiMo V2.5 (NovitaAI)","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.168,"output":0.336,"cache_read":0.0034,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo V2.5 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/qwen3.8-27b","name":"Qwen3.8 27B (NovitaAI)","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.42,"output":3,"cache_read":0.085},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B (NovitaAI)","type":"chat"},{"id":"novita/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking (NovitaAI)","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.98,"output":3.95},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-thinking","display_name":"Qwen3 VL 235B A22B Thinking (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B (NovitaAI)","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/glm-5.3-flash","name":"GLM-5.3 Flash (NovitaAI)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/glm-4.6","name":"GLM-4.6 (NovitaAI)","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507 (NovitaAI)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.09,"output":0.58},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B A22B Instruct 2507 (NovitaAI)","type":"chat"},{"id":"novita/qwen3.8-max","name":"Qwen3.8 Max (NovitaAI)","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/kimi-k3","name":"Kimi K3 (NovitaAI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct (NovitaAI)","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8192},"cost":{"input":0.27,"output":0.85},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct (NovitaAI)","type":"chat"},{"id":"novita/glm-5","name":"GLM-5 (NovitaAI)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (NovitaAI)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/minimax-m2.5","name":"MiniMax M2.5 (NovitaAI)","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax M2.5 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/kimi-k2.6","name":"Kimi K2.6 (NovitaAI)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.8,"output":3.4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"novita/qwen3-max","name":"Qwen3 Max (NovitaAI)","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.845,"output":3.38},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/glm-4.5v","name":"GLM-4.5V (NovitaAI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM-4.5V (NovitaAI)","type":"chat"},{"id":"novita/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct (NovitaAI)","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.18,"output":0.59},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B Instruct (NovitaAI)","type":"chat"},{"id":"novita/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B FP8 (NovitaAI)","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":20000},"cost":{"input":0.2,"output":0.8},"display_name":"Qwen3 235B A22B FP8 (NovitaAI)","type":"chat"},{"id":"novita/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct (NovitaAI)","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.38,"output":1.55},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3 Coder 480B A35B Instruct (NovitaAI)","type":"chat"},{"id":"novita/qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct (NovitaAI)","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":32768},"cost":{"input":0.07,"output":0.27},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3 Coder 30B A3B Instruct (NovitaAI)","type":"chat"},{"id":"novita/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash (NovitaAI)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"display_name":"InclusionAI Ling 3.0 Flash (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct (NovitaAI)","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.7},"display_name":"Qwen3 VL 30B A3B Instruct (NovitaAI)","type":"chat"},{"id":"novita/ling-3.1-flash","name":"Ling 3.1 Flash (NovitaAI)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"inclusionai/ling-3.1-flash","display_name":"Ling 3.1 Flash (NovitaAI)","type":"chat"},{"id":"novita/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT (NovitaAI)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.4},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT (NovitaAI)","type":"chat"},{"id":"novita/llama-3-70b-instruct","name":"Llama 3 70B Instruct (NovitaAI)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-04-18","last_updated":"2024-04-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8000},"cost":{"input":0.51,"output":0.74},"display_name":"Llama 3 70B Instruct (NovitaAI)","type":"chat"},{"id":"novita/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507 (NovitaAI)","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":3},"display_name":"Qwen3 235B A22B Thinking 2507 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B (NovitaAI)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B A10B (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct (NovitaAI)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":120000},"cost":{"input":0.135,"output":0.4},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct (NovitaAI)","type":"chat"},{"id":"novita/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B (NovitaAI)","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.248,"output":1.485},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct (NovitaAI)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.5},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3 Next 80B A3B Instruct (NovitaAI)","type":"chat"},{"id":"novita/minimax-m2.7","name":"MiniMax M2.7 (NovitaAI)","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/mimo-v2.5-pro","name":"MiMo V2.5 Pro (NovitaAI)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.522,"output":1.044,"cache_read":0.0043,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/glm-4.7","name":"GLM-4.7 (NovitaAI)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"novita/qwen3.8-flash","name":"Qwen3.8 Flash (NovitaAI)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/qwen35-397b-a17b","name":"Qwen3.5 397B A17B (NovitaAI)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":64000},"cost":{"input":0.6,"output":3.6},"display_name":"Qwen3.5 397B A17B (NovitaAI)","type":"chat"},{"id":"novita/glm-5.2","name":"GLM-5.2 (NovitaAI)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"novita/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B (NovitaAI)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":123000,"output":16000},"cost":{"input":0.42,"output":1.25},"display_name":"ERNIE 4.5 VL 424B A47B (NovitaAI)","type":"chat"},{"id":"novita/hy3","name":"Hy3 (NovitaAI)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":262144},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"canonical_model_id":"tencent/hy3","display_name":"Hy3 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/kimi-k2","name":"Kimi K2 (NovitaAI)","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.57,"output":2.3},"display_name":"Kimi K2 (NovitaAI)","type":"chat"},{"id":"novita/glm-5.1","name":"GLM-5.1 (NovitaAI)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1.38,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"novita/step-3.7-flash","name":"Step 3.7 Flash (NovitaAI)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash (NovitaAI)","type":"chat"},{"id":"novita/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct (NovitaAI)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32000},"cost":{"input":0.03,"output":0.05},"display_name":"Llama 3.2 3B Instruct (NovitaAI)","type":"chat"},{"id":"novita/deepseek-v3.2","name":"DeepSeek V3.2 (NovitaAI)","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.269,"output":0.4,"cache_read":0.1345},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/glm-5.3","name":"GLM-5.3 (NovitaAI)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/kimi-k2.7-code","name":"Kimi K2.7 Code (NovitaAI)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"novita/minimax-m2.1","name":"MiniMax M2.1 (NovitaAI)","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax M2.1 (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"novita/deepseek-v4-flash","name":"DeepSeek V4 Flash (NovitaAI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (NovitaAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"embercloud/glm-4.5","name":"GLM-4.5 (EmberCloud)","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":96000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5 (EmberCloud)","type":"chat"},{"id":"embercloud/qwen3-coder-next","name":"Qwen3 Coder Next (EmberCloud)","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.108,"output":0.675,"cache_read":0.06},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next (EmberCloud)","type":"chat"},{"id":"embercloud/glm-5","name":"GLM-5 (EmberCloud)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131000},"cost":{"input":0.72,"output":2.3,"cache_read":0.144},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5 (EmberCloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"embercloud/kimi-k2.5","name":"Kimi K2.5 (EmberCloud)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.405,"output":1.98,"cache_read":0.225},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 (EmberCloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"embercloud/glm-4.7-flash","name":"GLM-4.7 Flash (EmberCloud)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131000},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7 Flash (EmberCloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"embercloud/glm-4.7","name":"GLM-4.7 (EmberCloud)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131000},"cost":{"input":0.38,"output":1.98,"cache_read":0.19},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7 (EmberCloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"embercloud/glm-5.2","name":"GLM-5.2 (EmberCloud)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131000},"cost":{"input":1.26,"output":3.96,"cache_read":0.234},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (EmberCloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"embercloud/glm-5.1","name":"GLM-5.1 (EmberCloud)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131000},"cost":{"input":0.931,"output":2.93,"cache_read":0.173},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1 (EmberCloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"embercloud/glm-4.5-air","name":"GLM-4.5 Air (EmberCloud)","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":96000},"cost":{"input":0.13,"output":0.85,"cache_read":0.025},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5 Air (EmberCloud)","type":"chat"},{"id":"perplexity/sonar","name":"Sonar (Perplexity)","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":130000,"output":4096},"cost":{"input":0.25,"output":2.5,"cache_write":0.25},"canonical_model_id":"perplexity/sonar","display_name":"Sonar (Perplexity)","type":"chat"},{"id":"azure-ai-foundry/grok-4-1-fast-reasoning","name":"Grok 4.1 Fast Reasoning (Azure AI Foundry)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"display_name":"Grok 4.1 Fast Reasoning (Azure AI Foundry)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"azure-ai-foundry/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"display_name":"Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)","type":"chat"},{"id":"azure-ai-foundry/grok-4-3","name":"Grok 4.3 (Azure AI Foundry)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":20000,"output":8192},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.3 (Azure AI Foundry)","type":"chat"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3 (Meta)","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3 (Meta)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1 (Meta)","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1 (Meta)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2 (Meta)","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2 (Meta)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-wonder-1.0","name":"Muse Wonder 1.0 (Meta)","description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"meta/muse-wonder-1.0","display_name":"Muse Wonder 1.0 (Meta)","type":"chat"},{"id":"azure/gpt-5.4","name":"GPT-5.4 (Azure)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4 (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.4-pro","name":"GPT-5.4 Pro (Azure)","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.4-nano","name":"GPT-5.4 Nano (Azure)","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 Nano (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.2-codex","name":"GPT-5.2 Codex (Azure)","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.1-codex","name":"GPT-5.1 Codex (Azure)","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":1.25,"output":10},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1 Codex (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-4o","name":"GPT-4o (Azure)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o (Azure)","type":"chat"},{"id":"azure/gpt-5-mini","name":"GPT-5 Mini (Azure)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.3-codex","name":"GPT-5.3 Codex (Azure)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5-nano","name":"GPT-5 Nano (Azure)","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-6.1-sol","name":"GPT-6.1 Sol (Azure)","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol (Azure)","type":"chat"},{"id":"azure/gpt-6-astra","name":"GPT-6 Astra (Azure)","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"azure/gpt-5.1","name":"GPT-5.1 (Azure)","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1 (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.4-mini","name":"GPT-5.4 Mini (Azure)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.6-luna","name":"GPT-5.6 Luna (Azure)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.2","name":"GPT-5.2 (Azure)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2 (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.5","name":"GPT-5.5 (Azure)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5 (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-4.1","name":"GPT-4.1 (Azure)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1 (Azure)","type":"chat"},{"id":"azure/gpt-4.1-mini","name":"GPT-4.1 Mini (Azure)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 Mini (Azure)","type":"chat"},{"id":"azure/gpt-6-luna","name":"GPT-6 Luna (Azure)","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna (Azure)","type":"chat"},{"id":"azure/gpt-5.6-terra","name":"GPT-5.6 Terra (Azure)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-oss-120b","name":"GPT OSS 120B (Azure)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"azure/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini (Azure)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5","name":"GPT-5 (Azure)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5 (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.6-sol","name":"GPT-5.6 Sol (Azure)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-6-sol","name":"GPT-6 Sol (Azure)","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol (Azure)","type":"chat"},{"id":"alibaba/qwen-flash","name":"Qwen Flash (Alibaba Cloud)","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0.0625},"canonical_model_id":"alibaba/qwen-flash","display_name":"Qwen Flash (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.7-max","name":"Qwen3.7 Max (Alibaba Cloud)","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3-vl-plus","name":"Qwen3 VL Plus (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":1.6,"cache_read":0.04,"cache_write":0.25},"canonical_model_id":"alibaba/qwen3-vl-plus","display_name":"Qwen3 VL Plus (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.5-27b","name":"Qwen3.5 27B (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen-max","name":"Qwen Max (Alibaba Cloud)","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4},"canonical_model_id":"alibaba/qwen-max","display_name":"Qwen Max (Alibaba Cloud)","type":"chat"},{"id":"alibaba/qwen3.8-max","name":"Qwen3.8 Max (Alibaba Cloud)","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/kimi-k3","name":"Kimi K3 (Alibaba Cloud)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/glm-5","name":"GLM-5 (Alibaba Cloud)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.573,"output":2.58},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5 (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Alibaba Cloud)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen-plus","name":"Qwen Plus (Alibaba Cloud)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32000},"cost":{"input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.7-flash","name":"Qwen3.7 Flash (Alibaba Cloud)","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":991808,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.0375},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B A10B (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/kimi-k2.5","name":"Kimi K2.5 (Alibaba Cloud)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.574,"output":3.011},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B (Alibaba Cloud)","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.375,"output":2.25},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.6-flash","name":"Qwen3.6 Flash (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.05,"cache_write":0.3125},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3-coder-flash","name":"Qwen3 Coder Flash (Alibaba Cloud)","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":997952,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash (Alibaba Cloud)","type":"chat"},{"id":"alibaba/qwen3.8-flash","name":"Qwen3.8 Flash (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen35-397b-a17b","name":"Qwen3.5 397B A17B (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"display_name":"Qwen3.5 397B A17B (Alibaba Cloud)","type":"chat"},{"id":"alibaba/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B A3B (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/glm-5.2","name":"GLM-5.2 (Alibaba Cloud)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.28},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"alibaba/deepseek-v4-pro","name":"DeepSeek V4 Pro (Alibaba Cloud)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":2.4,"output":4.8,"cache_read":0.2},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"alibaba/qwen3.6-plus","name":"Qwen3.6 Plus (Alibaba Cloud)","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen-plus-latest","name":"Qwen Plus Latest (Alibaba Cloud)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-09-09","last_updated":"2024-09-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5},"display_name":"Qwen Plus Latest (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/glm-5.3","name":"GLM-5.3 (Alibaba Cloud)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.28},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3.7-plus","name":"Qwen3.7 Plus (Alibaba Cloud)","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/deepseek-v4-flash","name":"DeepSeek V4 Flash (Alibaba Cloud)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.2,"output":0.4,"cache_read":0.04},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Alibaba Cloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"baidu/glm-5","name":"GLM-5 (Baidu)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5 (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"baidu/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Baidu)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"baidu/kimi-k2.6","name":"Kimi K2.6 (Baidu)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"baidu/glm-5.2","name":"GLM-5.2 (Baidu)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"baidu/glm-5.1","name":"GLM-5.1 (Baidu)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1 (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"baidu/deepseek-v4-pro","name":"DeepSeek V4 Pro (Baidu)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.32,"output":3.96,"cache_read":0.042},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"baidu/glm-5.3","name":"GLM-5.3 (Baidu)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"baidu/deepseek-v4-flash","name":"DeepSeek V4 Flash (Baidu)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Baidu)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"gonka24/minimax-m2.7","name":"MiniMax M2.7 (Gonka24)","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.08,"output":0.32,"cache_read":0.017},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7 (Gonka24)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"reka-ai/reka-edge-2603","name":"Reka Edge 2603 (reka-ai)","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-09","last_updated":"2026-10-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"cost":{"input":0.1,"output":0.1},"display_name":"Reka Edge 2603 (reka-ai)","type":"chat"},{"id":"reka-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro (reka-ai)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":1.2,"output":3.3,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (reka-ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"reka-ai/glm-5.3","name":"GLM-5.3 (reka-ai)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.17,"output":3.96,"cache_read":0.234},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (reka-ai)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bytedance/seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.07,"output":0.3,"cache_read":0.015},"display_name":"Seed 1.6 Flash (250715) (ByteDance)","type":"chat"},{"id":"bytedance/seed-2-0-code-preview-260328","name":"Seed 2.0 Code Preview (260328) (ByteDance)","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1},"display_name":"Seed 2.0 Code Preview (260328) (ByteDance)","type":"chat"},{"id":"bytedance/seed-1-6-250915","name":"Seed 1.6 (250915) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 1.6 (250915) (ByteDance)","type":"chat"},{"id":"bytedance/seed-2-0-mini-260428","name":"Seed 2.0 Mini (260428) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.1,"output":0.4,"cache_read":0.02},"display_name":"Seed 2.0 Mini (260428) (ByteDance)","type":"chat"},{"id":"bytedance/seed-2-0-pro-260328","name":"Seed 2.0 Pro (260328) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1},"display_name":"Seed 2.0 Pro (260328) (ByteDance)","type":"chat"},{"id":"bytedance/seed-1-8-251228","name":"Seed 1.8 (251228) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 1.8 (251228) (ByteDance)","type":"chat"},{"id":"bytedance/glm-4.7","name":"GLM-4.7 (ByteDance)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7 (ByteDance)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bytedance/seed-1-6-250615","name":"Seed 1.6 (250615) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 1.6 (250615) (ByteDance)","type":"chat"},{"id":"bytedance/glm-5.2","name":"GLM-5.2 (ByteDance)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (ByteDance)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"bytedance/seed-2-0-lite-260428","name":"Seed 2.0 Lite (260428) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 2.0 Lite (260428) (ByteDance)","type":"chat"},{"id":"bytedance/deepseek-v4-pro","name":"DeepSeek V4 Pro (ByteDance)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (ByteDance)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"bytedance/deepseek-v3.2","name":"DeepSeek V3.2 (ByteDance)","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.28,"output":0.42,"cache_read":0.056},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2 (ByteDance)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bytedance/gpt-oss-120b","name":"GPT OSS 120B (ByteDance)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.1,"output":0.5,"cache_read":0.02},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (ByteDance)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bytedance/deepseek-v4-flash","name":"DeepSeek V4 Flash (ByteDance)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (ByteDance)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"sciforium/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (sciforium)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.246,"output":0.944,"cache_read":0.012},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (sciforium)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4-5","name":"Grok 4.5 (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"display_name":"Grok 4.5 (xAI)","type":"chat"},{"id":"xai/grok-build-0-1","name":"Grok Build 0.1 (xAI)","description":"Grok coding model for agentic engineering, edits, and codebase workflows","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-20","last_updated":"2026-05-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"display_name":"Grok Build 0.1 (xAI)","type":"chat"},{"id":"xai/grok-4","name":"Grok 4 (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":3,"output":15,"cache_read":0.75},"display_name":"Grok 4 (xAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4-20-beta-0309-non-reasoning","name":"Grok 4.20 Beta Non-Reasoning (0309) (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Beta Non-Reasoning (0309) (xAI)","type":"chat"},{"id":"xai/grok-4-3","name":"Grok 4.3 (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.3 (xAI)","type":"chat"},{"id":"xai/grok-4-20-beta-0309-reasoning","name":"Grok 4.20 Beta Reasoning (0309) (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Beta Reasoning (0309) (xAI)","type":"chat"},{"id":"xai/grok-4-6","name":"Grok 4.6 (xAI)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6 (xAI)","type":"chat"},{"id":"xai/grok-4-7","name":"Grok 4.7 (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"display_name":"Grok 4.7 (xAI)","type":"chat"},{"id":"ranoai/deepseek-v4-flash","name":"DeepSeek V4 Flash (RanoAI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (RanoAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"canopywave/kimi-k3","name":"Kimi K3 (CanopyWave)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (CanopyWave)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"canopywave/kimi-k2.6","name":"Kimi K2.6 (CanopyWave)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (CanopyWave)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"canopywave/glm-5.2","name":"GLM-5.2 (CanopyWave)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (CanopyWave)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"canopywave/deepseek-v4-pro","name":"DeepSeek V4 Pro (CanopyWave)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.74,"output":3.48,"cache_read":0.01},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (CanopyWave)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"canopywave/deepseek-v4-flash","name":"DeepSeek V4 Flash (CanopyWave)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (CanopyWave)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"fireworks/glm-5.3-flash","name":"GLM-5.3 Flash (Fireworks AI)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (Fireworks AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/kimi-k3","name":"Kimi K3 (Fireworks AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1040384,"output":1040384},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Fireworks AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Fireworks AI)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Fireworks AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/kimi-k3-fast","name":"Kimi K3 Fast (Fireworks AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1040384,"output":1040384},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 Fast (Fireworks AI)","type":"chat"},{"id":"fireworks/glm-5.3","name":"GLM-5.3 (Fireworks AI)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Fireworks AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/deepseek-v4-flash","name":"DeepSeek V4 Flash (Fireworks AI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Fireworks AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"sakana/fugu-max","name":"Fugu Max (Sakana AI)","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2,"output":6,"cache_read":0.25},"display_name":"Fugu Max (Sakana AI)","type":"chat"},{"id":"sakana/fugu-ultra-v2.0","name":"Fugu Ultra v2.0 (Sakana AI)","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5},"display_name":"Fugu Ultra v2.0 (Sakana AI)","type":"chat"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra (Sakana AI)","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra (Sakana AI)","type":"chat"},{"id":"scx-ai/qwen3-32b","name":"Qwen3 32B (SCX.ai (Turbo))","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.36,"output":0.87},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B (SCX.ai (Turbo))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"scx-ai/minimax-m2.7","name":"MiniMax M2.7 (SCX.ai (Turbo))","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.48,"output":1.79,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7 (SCX.ai (Turbo))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"scx-ai/gpt-oss-120b","name":"GPT OSS 120B (SCX.ai (Turbo))","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.17,"output":0.55},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (SCX.ai (Turbo))","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B (Together AI)","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1010000,"output":909000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/glm-5.3-flash","name":"GLM-5.3 Flash (Together AI)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943717},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/muse-glimmer-30b","name":"Muse Glimmer 30B (Together AI)","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":117964},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B (Together AI)","type":"chat"},{"id":"together-ai/kimi-k3","name":"Kimi K3 (Together AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1000000},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Together AI)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/glm-4.7","name":"GLM-4.7 (Together AI)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0.45,"output":2},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7 (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"together-ai/minimax-m3","name":"MiniMax M3 (Together AI)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3 (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro (Together AI)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":163840},"cost":{"input":1.32,"output":3.96,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"together-ai/gpt-oss-120b","name":"GPT OSS 120B (Together AI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/glm-5.3","name":"GLM-5.3 (Together AI)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943717},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together-ai/deepseek-v4-flash","name":"DeepSeek V4 Flash (Together AI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"xiaomi/mimo-v2.6-pro","name":"MiMo V2.6 Pro (Xiaomi)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo V2.6 Pro (Xiaomi)","type":"chat"},{"id":"xiaomi/mimo-v2.6-flash","name":"MiMo V2.6 Flash (Xiaomi)","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo V2.6 Flash (Xiaomi)","type":"chat"},{"id":"quartz/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview) (Quartz)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro (Preview) (Quartz)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5 (MiniMax)","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax M2.5 (MiniMax)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax M2.1 Lightning (MiniMax)","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":131072},"cost":{"input":0.12,"output":0.48},"display_name":"MiniMax M2.1 Lightning (MiniMax)","type":"chat"},{"id":"minimax/minimax-text-01","name":"MiniMax Text 01 (MiniMax)","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.2,"output":1.1},"display_name":"MiniMax Text 01 (MiniMax)","type":"chat"},{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7 (MiniMax)","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7 (MiniMax)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax M3 (MiniMax)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3 (MiniMax)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 Highspeed (MiniMax)","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.6,"output":2.4,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax M2.7 Highspeed (MiniMax)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5 Highspeed (MiniMax)","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.6,"output":2.4,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5-highspeed","display_name":"MiniMax M2.5 Highspeed (MiniMax)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1 (MiniMax)","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.27,"output":1.1},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax M2.1 (MiniMax)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2","name":"MiniMax M2 (MiniMax)","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.2,"output":1,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax M2 (MiniMax)","type":"chat"},{"id":"inference.net/glm-5.3-flash","name":"GLM-5.3 Flash (Inference.net)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.09,"output":0.28,"cache_read":0.02},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash (Inference.net)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inference.net/llama-3.2-11b-instruct","name":"Llama 3.2 11B Instruct (Inference.net)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.07,"output":0.33},"display_name":"Llama 3.2 11B Instruct (Inference.net)","type":"chat"},{"id":"inference.net/glm-5.3","name":"GLM-5.3 (Inference.net)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.9,"output":3,"cache_read":0.15},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Inference.net)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inference.net/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017 (Inference.net)","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.3,"output":1,"cache_read":0.007},"display_name":"DeepSeek V4.1 Flash 1017 (Inference.net)","type":"chat"},{"id":"azure-anthropic/claude-opus-5-5","name":"Claude Opus 5.5 (Azure Anthropic)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (Azure Anthropic)","type":"chat"},{"id":"azure-anthropic/claude-fable-5-1","name":"Claude Fable 5.1 (Azure Anthropic)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1 (Azure Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"azure-anthropic/claude-opus-5","name":"Claude Opus 5 (Azure Anthropic)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (Azure Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"azure-anthropic/claude-fable-5","name":"Claude Fable 5 (Azure Anthropic)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5 (Azure Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"azure-anthropic/claude-opus-4-8","name":"Claude Opus 4.8 (Azure Anthropic)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (Azure Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"azure-anthropic/claude-sonnet-5","name":"Claude Sonnet 5 (Azure Anthropic)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (Azure Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"azure-anthropic/claude-opus-4-6","name":"Claude Opus 4.6 (Azure Anthropic)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (Azure Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"azure-anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5 (Azure Anthropic)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 (Azure Anthropic)","type":"chat"},{"id":"azure-anthropic/claude-opus-4-7","name":"Claude Opus 4.7 (Azure Anthropic)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (Azure Anthropic)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"mistral/mistral-large-latest","name":"Mistral Large Latest (Mistral AI)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":262144},"cost":{"input":4,"output":12},"canonical_model_id":"mistral/mistral-large-latest","display_name":"Mistral Large Latest (Mistral AI)","type":"chat"},{"id":"mistral/ministral-8b-2512","name":"Ministral 8B (Mistral AI)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":0.15},"display_name":"Ministral 8B (Mistral AI)","type":"chat"},{"id":"mistral/mistral-large-4","name":"Mistral Large 4 (Mistral AI)","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":262144},"cost":{"input":1.36,"output":4.18,"cache_read":0.14},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4 (Mistral AI)","type":"chat"},{"id":"mistral/devstral-2512","name":"Devstral 2 (Mistral AI)","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2 (Mistral AI)","type":"chat"},{"id":"mistral/mistral-medium-3-5","name":"Mistral Medium 3.5 (Mistral AI)","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"display_name":"Mistral Medium 3.5 (Mistral AI)","type":"chat"},{"id":"mistral/mistral-small-2603","name":"Mistral Small 4 (Mistral AI)","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4 (Mistral AI)","type":"chat"},{"id":"mistral/mistral-large-2512","name":"Mistral Large 3 (Mistral AI)","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3 (Mistral AI)","type":"chat"},{"id":"mistral/ministral-14b-2512","name":"Ministral 14B (Mistral AI)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.2},"display_name":"Ministral 14B (Mistral AI)","type":"chat"},{"id":"mistral/mistral-small-2506","name":"Mistral Small 3.2 (Mistral AI)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/mistral-small-2506","display_name":"Mistral Small 3.2 (Mistral AI)","type":"chat"},{"id":"mistral/ministral-3b-2512","name":"Ministral 3B (Mistral AI)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.1},"display_name":"Ministral 3B (Mistral AI)","type":"chat"},{"id":"mistral/glm-5.3","name":"GLM-5.3 (Mistral AI)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Mistral AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral/codestral-2508","name":"Codestral (Mistral AI)","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":0.9},"display_name":"Codestral (Mistral AI)","type":"chat"},{"id":"vertex-anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (Vertex AI (Anthropic))","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (Vertex AI (Anthropic))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"vertex-anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (Vertex AI (Anthropic))","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (Vertex AI (Anthropic))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"vertex-anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (Vertex AI (Anthropic))","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5 (Vertex AI (Anthropic))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"vertex-anthropic/claude-sonnet-5","name":"Claude Sonnet 5 (Vertex AI (Anthropic))","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (Vertex AI (Anthropic))","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"vertex-anthropic/claude-opus-4-6","name":"Claude Opus 4.6 (Vertex AI (Anthropic))","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (Vertex AI (Anthropic))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"vertex-anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6 (Vertex AI (Anthropic))","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (Vertex AI (Anthropic))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"vertex-anthropic/claude-opus-4-7","name":"Claude Opus 4.7 (Vertex AI (Anthropic))","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (Vertex AI (Anthropic))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"vertex-openai/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible))","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.22,"output":0.88},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible))","type":"chat"},{"id":"vertex-openai/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-thinking","display_name":"Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"vertex-openai/glm-5","name":"GLM-5 (Vertex AI (OpenAI-compatible))","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":32768},"cost":{"input":1,"output":3.2,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5 (Vertex AI (OpenAI-compatible))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"vertex-openai/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI-compatible))","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.22,"output":1.8,"cache_read":0.022},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI-compatible))","type":"chat"},{"id":"vertex-openai/kimi-k2-thinking","name":"Kimi K2 Thinking (Vertex AI (OpenAI-compatible))","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":2.5,"cache_read":0.06},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking (Vertex AI (OpenAI-compatible))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"vertex-openai/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible))","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible))","type":"chat"},{"id":"vertex-openai/glm-4.7","name":"GLM-4.7 (Vertex AI (OpenAI-compatible))","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0.6,"output":2.2},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7 (Vertex AI (OpenAI-compatible))","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"vertex-openai/grok-4-20-non-reasoning","name":"Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"grok","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"vertex-openai/grok-4-6","name":"Grok 4.6 (Vertex AI (OpenAI-compatible))","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6 (Vertex AI (OpenAI-compatible))","type":"chat"},{"id":"vertex-openai/grok-4-20-reasoning","name":"Grok 4.20 Reasoning (Vertex AI (OpenAI-compatible))","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Reasoning (Vertex AI (OpenAI-compatible))","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"vertex-openai/deepseek-v3.2","name":"DeepSeek V3.2 (Vertex AI (OpenAI-compatible))","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.56,"output":1.68,"cache_read":0.056},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2 (Vertex AI (OpenAI-compatible))","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google-vertex/gemini-3.6-flash","name":"Gemini 3.6 Flash (Google Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-vertex/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite (Google Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google-vertex/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview) (Google Vertex AI)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro (Preview) (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-vertex/gemini-3.5-flash","name":"Gemini 3.5 Flash (Google Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-vertex/gemini-3.7-flash","name":"Gemini 3.7 Flash (Google Vertex AI)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-vertex/gemini-3-flash-preview","name":"Gemini 3 Flash (Preview) (Google Vertex AI)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash (Preview) (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-vertex/gemini-3.8-flash","name":"Gemini 3.8 Flash (Google Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"display_name":"Gemini 3.8 Flash (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google-vertex/gemini-4-argon","name":"Gemini 4 Argon (Google Vertex AI)","description":"Gemini multimodal model for text, image, audio, video, and document tasks","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-30","last_updated":"2026-09-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":0.375},"display_name":"Gemini 4 Argon (Google Vertex AI)","type":"chat"},{"id":"google-vertex/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite (Google Vertex AI)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite (Google Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"aws-mantle/gpt-6-astra","name":"GPT-6 Astra (AWS Mantle)","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra (AWS Mantle)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"aws-mantle/gpt-5.6-luna","name":"GPT-5.6 Luna (AWS Mantle)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":921600,"output":128000},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna (AWS Mantle)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"aws-mantle/gpt-5.6-terra","name":"GPT-5.6 Terra (AWS Mantle)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":921600,"output":128000},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra (AWS Mantle)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"aws-mantle/gpt-5.6-sol","name":"GPT-5.6 Sol (AWS Mantle)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":921600,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol (AWS Mantle)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4","name":"GPT-5.4 (OpenAI)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4 (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro (OpenAI)","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo (OpenAI)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5 Turbo (OpenAI)","type":"chat"},{"id":"openai/gpt-4o-transcribe","name":"GPT-4o Transcribe (OpenAI)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":2000},"cost":{"input":2.5,"output":10},"display_name":"GPT-4o Transcribe (OpenAI)","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro (OpenAI)","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 Nano (OpenAI)","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 Nano (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o (OpenAI)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o (OpenAI)","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini (OpenAI)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro (OpenAI)","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":21,"output":168},"canonical_model_id":"openai/gpt-5.2-pro","display_name":"GPT-5.2 Pro (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4 Mini (OpenAI)","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4 Mini (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3 Mini (OpenAI)","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3 Mini (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4","name":"GPT-4 (OpenAI)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"canonical_model_id":"openai/gpt-4","display_name":"GPT-4 (OpenAI)","type":"chat"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex (OpenAI)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 Nano (OpenAI)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 Nano (OpenAI)","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano (OpenAI)","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1","name":"o1 (OpenAI)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"canonical_model_id":"openai/o1","display_name":"o1 (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro (OpenAI)","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol (OpenAI)","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol (OpenAI)","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra (OpenAI)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-03","last_updated":"2026-09-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"GPT-6 Astra (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1","name":"GPT-5.1 (OpenAI)","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1 (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o Mini (OpenAI)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o Mini (OpenAI)","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini (OpenAI)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna (OpenAI)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2 (OpenAI)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2 (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5 (OpenAI)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5 (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1 (OpenAI)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1 (OpenAI)","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 Mini (OpenAI)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 Mini (OpenAI)","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna (OpenAI)","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna (OpenAI)","type":"chat"},{"id":"openai/gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe (OpenAI)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":2000},"cost":{"input":1.25,"output":5},"display_name":"GPT-4o Mini Transcribe (OpenAI)","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra (OpenAI)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo (OpenAI)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo (OpenAI)","type":"chat"},{"id":"openai/o3","name":"o3 (OpenAI)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3 (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5 (OpenAI)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5 (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol (OpenAI)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol (OpenAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol (OpenAI)","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol (OpenAI)","type":"chat"},{"id":"moonshot/kimi-k3","name":"Kimi K3 (Moonshot AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Moonshot AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed (Moonshot AI)","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed (Moonshot AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6 (Moonshot AI)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (Moonshot AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshot/kimi-k2.5","name":"Kimi K2.5 (Moonshot AI)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 (Moonshot AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code (Moonshot AI)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code (Moonshot AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"above":{"id":"above","api":"https://api.above.dev/v1","name":"above.dev","doc":"https://above.dev/docs","display_name":"above.dev","models":[{"id":"mimo-v2.6-pro","name":"MiMo V2.6 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.5077,"output":1.0154,"cache_read":0.0042},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo V2.6 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.165,"output":0.55,"cache_read":0.0319},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.2-fast","name":"GLM 5.2 Fast","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2.31,"output":7.26,"cache_read":0.231},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.8-max","name":"Qwen 3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2.2,"output":6.6,"cache_read":0.275},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen 3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.165,"output":0.66,"reasoning":0.66,"cache_read":0.0033},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"mimo-v2.6-pro-ultraspeed","name":"MiMo V2.6 Pro UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":5.0769,"output":10.1538,"cache_read":0.0423},"canonical_model_id":"xiaomi/mimo-v2.6-pro-ultraspeed","display_name":"MiMo V2.6 Pro UltraSpeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.6-flash","name":"MiMo V2.6 Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1692,"output":0.3385,"cache_read":0.0034},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo V2.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.54,"output":4.84,"cache_read":0.154},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.726,"output":2.178,"reasoning":2.178,"cache_read":0.0242},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"status":"deprecated","cost":{"input":0.165,"output":0.66,"reasoning":0.66,"cache_read":0.0033},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"kilo":{"id":"kilo","api":"https://api.kilo.ai/api/gateway","name":"Kilo Gateway","doc":"https://kilo.ai","display_name":"Kilo Gateway","models":[{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-08-13","last_updated":"2024-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":7372},"cost":{"input":0.04,"output":0.05},"display_name":"Sao10K: Llama 3 8B Lunaris","type":"chat"},{"id":"sao10k/l3.3-euryale-70b","name":"Sao10K: Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-12-18","last_updated":"2024-12-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.65,"output":0.75},"display_name":"Sao10K: Llama 3.3 Euryale 70B","type":"chat"},{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-08-28","last_updated":"2024-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.85,"output":0.85},"display_name":"Sao10K: Llama 3.1 Euryale 70B v2.2","type":"chat"},{"id":"stealth/claude-opus-4.6","name":"Stealth: Claude Opus 4.6 (20% off)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"reasoning":0,"cache_read":0.4,"cache_write":5},"display_name":"Stealth: Claude Opus 4.6 (20% off)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"stealth/claude-opus-4.7","name":"Stealth: Claude Opus 4.7 (20% off)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"reasoning":0,"cache_read":0.4,"cache_write":5},"display_name":"Stealth: Claude Opus 4.7 (20% off)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"stealth/claude-opus-4.8","name":"Stealth: Claude Opus 4.8 (20% off)","description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.8 is offered at 20% lower cost than standard Claude Opus 4.8 pricing and is not served by Anthropic or Kilo Code.","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"reasoning":0,"cache_read":0.4,"cache_write":5},"display_name":"Stealth: Claude Opus 4.8 (20% off)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"stealth/glyph-cluster","name":"Stealth: Glyph Cluster (free)","description":"Your prompts and completions may be retained and used to train or improve the provider's services. Glyph Cluster is a reasoning model for coding and long-context analysis, served through Vercel AI Gateway during its stealth period at no cost. It supports function calling and streaming, takes text input only, and does not support structured outputs. Zero Data Retention is not available for this model.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0,"reasoning":0,"cache_read":0},"display_name":"Stealth: Glyph Cluster (free)","type":"chat"},{"id":"stealth/claude-sonnet-4.6","name":"Stealth: Claude Sonnet 4.6 (20% off)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.4,"output":12,"reasoning":0,"cache_read":0.24,"cache_write":3},"display_name":"Stealth: Claude Sonnet 4.6 (20% off)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"stealth/qwen3.6-plus","name":"Stealth: Qwen3.6 Plus (50% off)","description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Qwen3.6 Plus is offered at 50% lower cost than standard Qwen3.6 Plus pricing and is not served by Alibaba or Kilo Code. Note: a surcharge applies to long-context workloads exceeding 256K input tokens.","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":0,"cache_read":0.025,"cache_write":0.3125},"display_name":"Stealth: Qwen3.6 Plus (50% off)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash (retires Nov 11)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.3},"display_name":"ByteDance Seed: Seed 1.6 Flash (retires Nov 11)","type":"chat"},{"id":"bytedance-seed/seed-2.0-lite","name":"Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.25,"output":2},"canonical_model_id":"bytedance-seed/seed-2.0-lite","display_name":"Seed 2.0 Lite","type":"chat"},{"id":"bytedance-seed/seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.5,"output":2.5},"display_name":"ByteDance Seed: Seed 2.1 Turbo","type":"chat"},{"id":"bytedance-seed/seed-2.0-mini","name":"Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.1,"output":0.4},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed 2.0 Mini","type":"chat"},{"id":"bytedance-seed/seed-2.0-code","name":"Seed 2.0 Code","description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":3},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code","type":"chat"},{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6 (retires Nov 11)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.25,"output":2},"display_name":"ByteDance Seed: Seed 1.6 (retires Nov 11)","type":"chat"},{"id":"~moonshotai/kimi-latest","name":"MoonshotAI: Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.249,"output":11.936,"cache_read":0.21},"display_name":"MoonshotAI: Kimi Latest","type":"chat"},{"id":"poolside/laguna-s-2.1:free","name":"Poolside: Laguna S 2.1 (free)","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","family":"laguna-s","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"display_name":"Poolside: Laguna S 2.1 (free)","type":"chat"},{"id":"poolside/laguna-s-2.1","name":"Poolside: Laguna S 2.1 (retires Oct 31)","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","family":"laguna-s","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"display_name":"Poolside: Laguna S 2.1 (retires Oct 31)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"poolside/laguna-xs-2.1:free","name":"Poolside: Laguna XS 2.1 (free)","description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"display_name":"Poolside: Laguna XS 2.1 (free)","type":"chat"},{"id":"poolside/laguna-xs-2.1","name":"Poolside: Laguna XS 2.1 (retires Oct 31)","description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.2,"cache_read":0.05},"display_name":"Poolside: Laguna XS 2.1 (retires Oct 31)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"prism-ml/ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.5,"cache_read":0.0375},"display_name":"PrismML: Ternary Bonsai 2 27B","type":"chat"},{"id":"anthropic/claude-opus-4.1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude Opus 4.1 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"nex-agi/nex-n2.5-mini","name":"Nex AGI: Nex-N2.5-Mini","description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","family":"agi","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.025,"output":0.1,"cache_read":0.0025},"display_name":"Nex AGI: Nex-N2.5-Mini","type":"chat"},{"id":"nex-agi/nex-n2.5-pro","name":"Nex AGI: Nex-N2.5-Pro","description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","family":"agi","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.075,"output":0.25,"cache_read":0.015},"display_name":"Nex AGI: Nex-N2.5-Pro","type":"chat"},{"id":"cohere/command-r-08-2024","name":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"cohere/command-r-08-2024","display_name":"Command R","type":"chat"},{"id":"cohere/command-a-plus","name":"Cohere: Command A+","description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","family":"command-a","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":64000},"cost":{"input":0.3,"output":1.5,"cache_read":0.15},"display_name":"Cohere: Command A+","type":"chat"},{"id":"cohere/command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a","display_name":"Command A","type":"chat"},{"id":"cohere/north-mini-code:free","name":"Cohere: North Mini Code (free)","description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","family":"north","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"display_name":"Cohere: North Mini Code (free)","type":"chat"},{"id":"cohere/command-r7b-12-2024","name":"Command R7B","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"canonical_model_id":"cohere/command-r7b-12-2024","display_name":"Command R7B","type":"chat"},{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-r-plus-08-2024","display_name":"Command R+","type":"chat"},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.25,"output":0.95,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-chat-v3.1","display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":0.44,"output":1.32,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task...","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":0.2156,"output":0.6468,"cache_read":0.00686},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":147456},"cost":{"input":0.27,"output":1},"display_name":"DeepSeek: DeepSeek V3.1 Terminus","type":"chat"},{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":16384},"cost":{"input":0.32,"output":0.89},"canonical_model_id":"deepseek/deepseek-chat","display_name":"DeepSeek Chat","type":"chat"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":147456},"cost":{"input":0.27,"output":0.41},"display_name":"DeepSeek: DeepSeek V3.2 Exp","type":"chat"},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07-31","release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":115200},"cost":{"input":0.29,"output":1.14,"cache_read":0.11},"canonical_model_id":"deepseek/deepseek-chat-v3-0324","display_name":"DeepSeek V3 0324","type":"chat"},{"id":"deepseek/deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16000},"cost":{"input":0.7,"output":2.5},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":384000},"cost":{"input":1.6,"output":3.2,"cache_read":0.135},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.7,"output":2.5,"cache_read":0.35},"canonical_model_id":"deepseek/deepseek-r1-0528","display_name":"DeepSeek R1 0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.28,"output":0.42,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":943717},"cost":{"input":0.091,"output":0.182,"cache_read":0.0182},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"unbiased/pareto-26.9","name":"Pareto 26.9","description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":2.5,"output":7.5,"cache_read":0.25},"display_name":"Pareto 26.9","type":"chat"},{"id":"unbiased/pareto-26.10","name":"Pareto 26.10","description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.8,"output":3.2,"cache_read":0.03},"display_name":"Pareto 26.10","type":"chat"},{"id":"tencent/hy3-preview","name":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.18,"output":0.6,"cache_read":0.06},"canonical_model_id":"tencent/hy3-preview","display_name":"Hy3 preview","type":"chat"},{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":117964},"cost":{"input":0.14,"output":0.57},"display_name":"Tencent: Hunyuan A13B Instruct","type":"chat"},{"id":"tencent/hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.074,"output":0.295},"canonical_model_id":"tencent/hy-mt2-30b-a3b","display_name":"Hy-MT2-30B-A3B","type":"chat"},{"id":"tencent/hy-mt2-1.8b","name":"Hy-MT2-1.8B","description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.044,"output":0.177},"canonical_model_id":"tencent/hy-mt2-1.8b","display_name":"Hy-MT2-1.8B","type":"chat"},{"id":"tencent/hy3","name":"Hy3","description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":128000},"cost":{"input":0.0825,"output":0.33,"cache_read":0.020625},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy-mt2-7b","name":"Hy-MT2-7B","description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-19","last_updated":"2026-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.074,"output":0.295},"canonical_model_id":"tencent/hy-mt2-7b","display_name":"Hy-MT2-7B","type":"chat"},{"id":"tencent/hy4-preview","name":"Hy4 preview","description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":0.7506,"output":2.2509,"cache_read":0.0378},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":2.5,"output":5},"display_name":"Magnum v4 72B","type":"chat"},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":327680,"output":16384},"cost":{"input":0.08,"output":0.24},"display_name":"Meta: Llama 4 Scout","type":"chat"},{"id":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-04-30","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":16384},"cost":{"input":0.144,"output":0.144},"display_name":"Meta: Llama Guard 4 12B","type":"chat"},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.1875,"output":0.6525,"cache_read":0.05},"display_name":"Meta: Llama 4 Maverick","type":"chat"},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.1,"output":0.32},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":117964},"cost":{"input":0.02,"output":0.04},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama-3.1-8B-Instruct","type":"chat"},{"id":"meta-llama/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":60000,"output":54000},"cost":{"input":0.027,"output":0.201},"canonical_model_id":"meta/llama-3.2-1b-instruct","display_name":"Llama 3.2 1B Instruct","type":"chat"},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":117964},"cost":{"input":0.05,"output":0.33},"display_name":"Meta: Llama 3.2 3B Instruct","type":"chat"},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Llama-3.1-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.4,"output":0.4},"canonical_model_id":"meta/llama-3.1-70b-instruct","display_name":"Llama-3.1-70B-Instruct","type":"chat"},{"id":"~google/gemini-flash-latest","name":"Google: Gemini Flash Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667},"display_name":"Google: Gemini Flash Latest","type":"chat"},{"id":"~google/gemini-pro-latest","name":"Google: Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["audio","pdf","image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"reasoning":10,"cache_read":0.1,"cache_write":0.1875},"display_name":"Google: Gemini Pro Latest","type":"chat"},{"id":"~unbiased/pareto-latest","name":"Pareto Latest","description":"This model always redirects to the latest model in the Pareto family.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.8,"output":3.2,"cache_read":0.03},"display_name":"Pareto Latest","type":"chat"},{"id":"perceptron/perceptron-mk1","name":"Perceptron: Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.15,"output":1.5},"display_name":"Perceptron: Perceptron Mk1","type":"chat"},{"id":"perceptron/perceptron-mk1.5","name":"Perceptron: Perceptron Mk1.5","description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-25","last_updated":"2026-09-25","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":36864,"output":8192},"cost":{"input":0.15,"output":1.5},"display_name":"Perceptron: Perceptron Mk1.5","type":"chat"},{"id":"z-ai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.055},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM-4.6V","type":"chat"},{"id":"z-ai/glm-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"z-ai/glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.8,"output":8.8,"cache_read":0.56},"display_name":"Z.ai: GLM 5.3 Prime","type":"chat"},{"id":"z-ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM-5V-Turbo","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.5,"output":2,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM-4.5V","type":"chat"},{"id":"z-ai/glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.37,"output":1.25,"cache_read":0.09},"display_name":"Z.ai: GLM 5.3 FlashX","type":"chat"},{"id":"z-ai/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":117964},"cost":{"input":0.0605,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.54,"output":1.98,"cache_read":0.099},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.5-air","name":"GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.13,"output":0.85,"cache_read":0.025},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5-Air","type":"chat"},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"reflection/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.25,"output":1},"display_name":"Reflection: Beam 1.0 501B A23B","type":"chat"},{"id":"reflection/beam-free","name":"Reflection: Beam 1.0 (free)","description":"Your prompts and completions may be retained and used to train or improve the provider's services. Beam is Reflection's reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference, served through Vercel AI Gateway at no cost. It supports function calling, structured outputs, and streaming, and takes text input only. Zero Data Retention is not available for this model.","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"reasoning":0,"cache_read":0},"display_name":"Reflection: Beam 1.0 (free)","type":"chat"},{"id":"inference-net/schematron-v2-small","name":"Inference.net: Schematron V2 Small","description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-09-12","last_updated":"2026-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.05,"output":0.23,"cache_read":0.05},"display_name":"Inference.net: Schematron V2 Small","type":"chat"},{"id":"inference-net/schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-09-12","last_updated":"2026-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.03,"output":0.15,"cache_read":0.03},"display_name":"Inference.net: Schematron V2 Turbo","type":"chat"},{"id":"thinkingmachines/inkling-small:free","name":"Thinking Machines: Inkling Small (free)","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Thinking Machines: Inkling Small (free)","type":"chat"},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":262144},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat"},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":471859},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"meituan/longcat-2.0","name":"Meituan: LongCat 2.0","description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","family":"longcat","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-20","last_updated":"2026-07-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"output":262144},"cost":{"input":0.75,"output":3,"cache_read":0.015},"display_name":"Meituan: LongCat 2.0","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openrouter/bodybuilder","name":"Body Builder (beta)","description":"Preview model for early access evaluation, prototyping, and compatibility testing","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-15","last_updated":"2026-03-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"status":"beta","cost":{"input":0,"output":0},"display_name":"Body Builder (beta)","type":"chat"},{"id":"openrouter/free","name":"OpenRouter Free Models Router","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32768},"cost":{"input":0,"output":0},"display_name":"OpenRouter Free Models Router","type":"chat"},{"id":"openrouter/pareto-code","name":"Pareto Code Router","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-05-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":65536},"cost":{"input":0,"output":0},"display_name":"Pareto Code Router","type":"chat"},{"id":"openrouter/auto","name":"Auto Router","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-15","last_updated":"2026-03-15","modalities":{"input":["audio","image","pdf","text","video"],"output":["image","text"]},"open_weights":false,"limit":{"context":2000000,"output":32768},"cost":{"input":0,"output":0},"display_name":"Auto Router","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"cost":{"input":3,"output":15},"display_name":"Perplexity: Sonar Pro","type":"chat"},{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":115200},"cost":{"input":2,"output":8,"reasoning":3},"display_name":"Perplexity: Sonar Deep Research","type":"chat"},{"id":"perplexity/sonar","name":"Perplexity: Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127072,"output":114364},"cost":{"input":1,"output":1},"display_name":"Perplexity: Sonar","type":"chat"},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":115200},"cost":{"input":2,"output":8},"display_name":"Perplexity: Sonar Reasoning Pro","type":"chat"},{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-30","last_updated":"2025-10-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"cost":{"input":3,"output":15},"display_name":"Perplexity: Sonar Pro Search","type":"chat"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.3,"output":1.2,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat"},{"id":"meta/muse-wonder","name":"Meta: Muse Wonder","description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":4,"output":20,"cache_read":0.2},"display_name":"Meta: Muse Wonder","type":"chat"},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Meta: Muse Spark 1.2 Contributor","type":"chat"},{"id":"meta/muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Meta: Muse Spark 1.3 Contributor","type":"chat"},{"id":"meta/muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-08-18","last_updated":"2024-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.7,"output":0.7},"display_name":"Nous: Hermes 3 70B Instruct","type":"chat"},{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-08-16","last_updated":"2024-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":1,"output":1},"display_name":"Nous: Hermes 3 405B Instruct","type":"chat"},{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nousresearch","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":117964},"cost":{"input":1,"output":3},"display_name":"Nous: Hermes 4 405B","type":"chat"},{"id":"scaledown/summarize","name":"ScaleDown: Summarize","description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":4000},"cost":{"input":0.05,"output":0},"display_name":"ScaleDown: Summarize","type":"chat"},{"id":"scaledown/extract","name":"ScaleDown: Extract","description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":900000},"cost":{"input":0.05,"output":0},"display_name":"ScaleDown: Extract","type":"chat"},{"id":"~z-ai/glm-flash-latest","name":"Z.ai: GLM Flash Latest","description":"This model always redirects to the latest model in the GLM Flash family.","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.048,"output":0.2,"cache_read":0.006},"display_name":"Z.ai: GLM Flash Latest","type":"chat"},{"id":"~z-ai/glm-latest","name":"Z.ai: GLM Latest","description":"This model always redirects to the latest GLM model from Z.ai.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-19","last_updated":"2026-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.075,"output":2.2,"cache_read":0.07},"display_name":"Z.ai: GLM Latest","type":"chat"},{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":80000},"cost":{"input":0.25,"output":0.8,"cache_read":0.06},"canonical_model_id":"arcee-ai/trinity-large-thinking","display_name":"Trinity Large Thinking","type":"chat"},{"id":"~openai/gpt-terra-latest","name":"OpenAI: GPT Terra Latest","description":"This model always redirects to the latest model in the OpenAI GPT Terra family.","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"display_name":"OpenAI: GPT Terra Latest","type":"chat"},{"id":"~openai/gpt-luna-latest","name":"OpenAI: GPT Luna Latest","description":"This model always redirects to the latest model in the OpenAI GPT Luna family.","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"display_name":"OpenAI: GPT Luna Latest","type":"chat"},{"id":"~openai/gpt-sol-latest","name":"OpenAI: GPT Sol Latest","description":"This model always redirects to the latest model in the OpenAI GPT Sol family.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"display_name":"OpenAI: GPT Sol Latest","type":"chat"},{"id":"~openai/gpt-astra-latest","name":"OpenAI: GPT Astra Latest ($$$$)","description":"This model always redirects to the latest model in the OpenAI GPT Astra family.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"OpenAI: GPT Astra Latest ($$$$)","type":"chat"},{"id":"~openai/gpt-mini-latest","name":"OpenAI: GPT Mini Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"display_name":"OpenAI: GPT Mini Latest","type":"chat"},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.9},"display_name":"Venice: Uncensored","type":"chat"},{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-10","last_updated":"2025-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":29491},"cost":{"input":0.55,"output":0.8,"cache_read":0.25},"display_name":"TheDrummer: Skyfall 36B V2","type":"chat"},{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-11-08","last_updated":"2024-11-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1024000,"output":819200},"cost":{"input":0.4,"output":0.4},"display_name":"TheDrummer: UnslopNemo 12B","type":"chat"},{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-09-27","last_updated":"2025-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":117964},"cost":{"input":0.3,"output":0.5,"cache_read":0.15},"display_name":"TheDrummer: Cydonia 24B V4.1","type":"chat"},{"id":"x-ai/grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":1800000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"display_name":"SpaceXAI: Grok 4.20 Multi-Agent","type":"chat"},{"id":"x-ai/grok-4.7","name":"Grok 4.7","description":"Grok 4.7 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":450000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":900000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":450000},"cost":{"input":2,"output":6,"cache_read":0.3},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":230400},"cost":{"input":1,"output":2,"cache_read":0.2},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.20","name":"SpaceXAI: Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":1800000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"display_name":"SpaceXAI: Grok 4.20","type":"chat"},{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":450000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"elorian/glimpse","name":"Elorian: Glimpse","description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":256000},"cost":{"input":0.6,"output":3,"cache_read":0.06},"display_name":"Elorian: Glimpse","type":"chat"},{"id":"~anthropic/claude-opus-latest","name":"Anthropic: Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"display_name":"Anthropic: Claude Opus Latest","type":"chat"},{"id":"~anthropic/claude-haiku-latest","name":"Anthropic: Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"display_name":"Anthropic: Claude Haiku Latest","type":"chat"},{"id":"~anthropic/claude-sonnet-latest","name":"Anthropic: Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"display_name":"Anthropic: Claude Sonnet Latest","type":"chat"},{"id":"~anthropic/claude-fable-latest","name":"Anthropic: Claude Fable Latest ($$$$)","description":"This model always redirects to the latest model in the Claude Fable family.","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"display_name":"Anthropic: Claude Fable Latest ($$$$)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"upstage/solar-pro-3","name":"Upstage: Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":117964},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Upstage: Solar Pro 3","type":"chat"},{"id":"upstage/solar-pro4","name":"Upstage: Solar Pro 4","description":"Solar Pro 4 is a large language model from Upstage. It is suited for agentic workflows, office productivity, document-intensive work, and coding.","family":"solar","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"Upstage: Solar Pro 4","type":"chat"},{"id":"upstage/solar-mini4","name":"Upstage: Solar Mini 4","description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","family":"solar","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"display_name":"Upstage: Solar Mini 4","type":"chat"},{"id":"~deepseek/deepseek-flash-latest","name":"DeepSeek: DeepSeek Flash Latest","description":"This model always redirects to the latest model in the DeepSeek Flash family.","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-14","last_updated":"2026-09-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.05,"output":0.6,"cache_read":0.008},"display_name":"DeepSeek: DeepSeek Flash Latest","type":"chat"},{"id":"~deepseek/deepseek-pro-latest","name":"DeepSeek: DeepSeek Pro Latest","description":"This model always redirects to the latest model in the DeepSeek Pro family.","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-14","last_updated":"2026-09-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":393216},"cost":{"input":0.12,"output":8,"cache_read":0.12},"display_name":"DeepSeek: DeepSeek Pro Latest","type":"chat"},{"id":"~deepseek/deepseek-v4-flash-latest","name":"DeepSeek: DeepSeek V4 Flash Latest","description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-01","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":0.00392,"output":0.144,"cache_read":0.001523},"display_name":"DeepSeek: DeepSeek V4 Flash Latest","type":"chat"},{"id":"~x-ai/grok-latest","name":"xAI: Grok Latest","description":"This model always redirects to the latest Grok model from xAI.","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":450000},"cost":{"input":2,"output":6,"cache_read":0.5},"display_name":"xAI: Grok Latest","type":"chat"},{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":2048},"cost":{"input":0.1,"output":0.2,"cache_read":0.1},"display_name":"ByteDance: UI-TARS 7B ","type":"chat"},{"id":"liquid/lfm-2.5-2.6b:free","name":"LiquidAI: LFM2.5-2.6B (free)","description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","family":"liquid","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0,"output":0},"display_name":"LiquidAI: LFM2.5-2.6B (free)","type":"chat"},{"id":"liquid/lfm-2.5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","family":"liquid","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.05,"output":0.7,"cache_read":0.025},"display_name":"LiquidAI: LFM2.5-24B-A2B","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.1,"output":0.34,"cache_read":0.1},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":58982},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image-preview","display_name":"Nano Banana 2 Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/lyria-3-pro-preview","name":"Lyria 3 Pro Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/lyria-3-pro-preview","display_name":"Lyria 3 Pro Preview","type":"chat"},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":117964},"cost":{"input":0.08,"output":0.16},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT","type":"chat"},{"id":"google/gemini-2.5-flash-image","name":"Nano Banana","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Nano Banana","type":"image-generation"},{"id":"google/gemma-2-27b-it","name":"Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-07-13","last_updated":"2024-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"cost":{"input":0.65,"output":0.65},"canonical_model_id":"google/gemma-2-27b-it","display_name":"Gemma 2 27B","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.375,"output":1.875,"reasoning":1.875,"cache_read":0.0375,"cache_write":0.020833},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.042,"output":0.22,"cache_read":0.021},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":1,"output":6,"reasoning":6,"cache_read":0.1,"cache_write":0.1875},"canonical_model_id":"google/gemini-3-pro-image-preview","display_name":"Nano Banana Pro Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.15,"output":1.25,"reasoning":1.25,"cache_read":0.015,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/lyria-3-clip-preview","name":"Lyria 3 Clip Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/lyria-3-clip-preview","display_name":"Lyria 3 Clip Preview","type":"chat"},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1,"output":6,"reasoning":6,"cache_read":0.1,"cache_write":0.1875},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.04,"output":0.12},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT","type":"chat"},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":4.5,"reasoning":4.5,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":58982},"cost":{"input":0.25,"output":1.5},"canonical_model_id":"google/gemini-3.1-flash-lite-image","display_name":"Nano Banana 2 Lite","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.041667},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Gemini 3.8 Flash is Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.04,"output":0.05,"cache_read":0.02},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B IT","type":"chat"},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.1,"output":0.4,"reasoning":0.4,"cache_read":0.01,"cache_write":0.083333},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro-preview","name":"Gemini 2.5 Pro Preview 06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01-31","release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["pdf","image","text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375},"canonical_model_id":"google/gemini-2.5-pro-preview","display_name":"Gemini 2.5 Pro Preview 06-05","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.125,"output":0.75,"reasoning":0.75,"cache_read":0.0125,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"google/gemini-nano-banana-2.1","name":"Nano Banana 2.1","description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":58982},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"google/gemini-nano-banana-2.1","display_name":"Nano Banana 2.1","type":"image-generation"},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"reasoning":10,"cache_read":0.1,"cache_write":0.1875},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.125,"output":0.75,"reasoning":0.75,"cache_read":0.0125,"cache_write":0.041667},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"writer/palmyra-x5","name":"Writer: Palmyra X5","description":"General-purpose chat model for instruction following, writing, and analysis","family":"palmyra","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-21","last_updated":"2026-01-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1040000,"output":8192},"cost":{"input":0.6,"output":6},"display_name":"Writer: Palmyra X5","type":"chat"},{"id":"moondream/moondream3-preview","name":"Moondream: Moondream 3 Preview","description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":4096},"cost":{"input":0.3,"output":2.5},"display_name":"Moondream: Moondream 3 Preview","type":"chat"},{"id":"moondream/moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":4096},"cost":{"input":0.3,"output":2.5},"display_name":"Moondream: Moondream 3.1","type":"chat"},{"id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":117900},"cost":{"input":0.017,"output":0.112},"display_name":"IBM: Granite 4.0 Micro","type":"chat"},{"id":"ibm-granite/granite-4.2-8b","name":"IBM: Granite 4.2 8B","description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","family":"granite","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-31","last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":117964},"cost":{"input":0.06,"output":0.25,"cache_read":0.015},"display_name":"IBM: Granite 4.2 8B","type":"chat"},{"id":"fireworks/ember-1","name":"Fireworks: Ember-1","description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-24","last_updated":"2026-09-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":3,"output":15,"cache_read":0.3},"display_name":"Fireworks: Ember-1","type":"chat"},{"id":"mistralai/mistral-nemo","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.15,"output":0.15,"cache_read":0.015},"canonical_model_id":"mistral/mistral-nemo","display_name":"Mistral Nemo","type":"chat"},{"id":"mistralai/ministral-8b-2512","name":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.15,"output":0.15,"cache_read":0.015},"canonical_model_id":"mistral/ministral-8b-2512","display_name":"Ministral 3 8B 2512","type":"chat"},{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.05,"output":0.08},"canonical_model_id":"mistral/mistral-small-24b-instruct-2501","display_name":"Mistral Small 3","type":"chat"},{"id":"mistralai/devstral-2512","name":"Devstral 2","description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","family":"devstral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.4,"output":2,"cache_read":0.04},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"mistralai/mistral-saba","name":"Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":26214},"cost":{"input":0.2,"output":0.6,"cache_read":0.02},"canonical_model_id":"mistral/mistral-saba","display_name":"Saba","type":"chat"},{"id":"mistralai/mistral-medium-3-5","name":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":209715},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"mistral/mistral-medium-3-5","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"mistralai/mistral-medium-3.1","name":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":104857},"cost":{"input":0.4,"output":2,"cache_read":0.04},"canonical_model_id":"mistral/mistral-medium-3.1","display_name":"Mistral Medium 3.1","type":"chat"},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"canonical_model_id":"mistral/mistral-small-3.2-24b-instruct","display_name":"Mistral Small 3.2 24B","type":"chat"},{"id":"mistralai/mistral-large","name":"Mistral Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11-30","release_date":"2024-02-26","last_updated":"2024-02-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":102400},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"mistral/mistral-large","display_name":"Mistral Large","type":"chat"},{"id":"mistralai/mistral-small-2603","name":"Mistral Small 4","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"mistralai/mistral-medium-3","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":104857},"cost":{"input":0.4,"output":2,"cache_read":0.04},"canonical_model_id":"mistral/mistral-medium-3","display_name":"Mistral Medium 3","type":"chat"},{"id":"mistralai/voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":26214},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"canonical_model_id":"mistral/voxtral-small-24b-2507","display_name":"Voxtral Small 24B 2507","type":"chat"},{"id":"mistralai/mistral-large-2512","name":"Mistral Large 3","description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-03-31","release_date":"2024-11-19","last_updated":"2024-11-19","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":104857},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"mistral/mistral-large-2407","display_name":"Mistral Large 2407","type":"chat"},{"id":"mistralai/ministral-14b-2512","name":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"canonical_model_id":"mistral/ministral-14b-2512","display_name":"Ministral 3 14B 2512","type":"chat"},{"id":"mistralai/mistral-large-4-0","name":"Mistral: Mistral Large 4 (50% off)","description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up...","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":262144},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"display_name":"Mistral: Mistral Large 4 (50% off)","type":"chat"},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":102400},"cost":{"input":0.351,"output":0.555},"canonical_model_id":"mistral/mistral-small-3.1-24b-instruct","display_name":"Mistral Small 3.1 24B","type":"chat"},{"id":"mistralai/ministral-3b-2512","name":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":104857},"cost":{"input":0.1,"output":0.1,"cache_read":0.01},"canonical_model_id":"mistral/ministral-3b-2512","display_name":"Ministral 3 3B 2512","type":"chat"},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-01-31","release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":52428},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"mistral/mixtral-8x22b-instruct","display_name":"Mixtral 8x22B Instruct","type":"chat"},{"id":"mistralai/codestral-2508","name":"Codestral 25.08","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":204800},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 25.08","type":"chat"},{"id":"sakana/fugu-max","name":"Fugu Max","description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"sakana/fugu-max","display_name":"Fugu Max","type":"chat"},{"id":"sakana/fugu-ultra-v2","name":"Fugu Ultra v2","description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-08-28","release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"sakana/fugu-ultra-v2","display_name":"Fugu Ultra v2","type":"chat"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"sakana/sakana-namazu","name":"Sakana Namazu","description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","family":"sakana-namazu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.15},"canonical_model_id":"sakana/sakana-namazu","display_name":"Sakana Namazu","type":"chat"},{"id":"inclusionai/ling-3.0-flash","name":"inclusionAI: Ling 3.0 Flash","description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"display_name":"inclusionAI: Ling 3.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionai/ling-3.1-flash","name":"inclusionAI: Ling 3.1 Flash","description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-02","last_updated":"2026-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.3,"output":0.9,"cache_read":0.06},"display_name":"inclusionAI: Ling 3.1 Flash","type":"chat"},{"id":"inclusionai/ling-3.0-flash-vl","name":"inclusionAI: Ling 3.0 Flash VL","description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"display_name":"inclusionAI: Ling 3.0 Flash VL","type":"chat"},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.65,"output":3.41,"cache_read":0.15},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.6,"output":3},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 Instruct 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.6,"output":2.5},"canonical_model_id":"moonshotai/kimi-k2-0905","display_name":"Kimi K2 Instruct 0905","type":"chat"},{"id":"moonshotai/kimi-k2","name":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12-31","release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.57,"output":2.3},"canonical_model_id":"moonshotai/kimi-k2","display_name":"Kimi K2 0711","type":"chat"},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.6712,"output":3.35,"cache_read":0.18},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kilo-auto/small","name":"Auto Small","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.4,"reasoning":0,"cache_read":0.005},"display_name":"Auto Small","type":"chat"},{"id":"kilo-auto/efficient","name":"Auto Efficient","description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","family":"auto","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.325,"output":1.95,"reasoning":0,"cache_read":0.0325,"cache_write":0.40625},"display_name":"Auto Efficient","type":"chat"},{"id":"kilo-auto/free","name":"Auto Free","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32768},"cost":{"input":0,"output":0,"reasoning":0,"cache_read":0,"cache_write":0},"display_name":"Auto Free","type":"chat"},{"id":"kilo-auto/frontier","name":"Auto Frontier","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"reasoning":0,"cache_read":0.5,"cache_write":6.25},"display_name":"Auto Frontier","type":"chat"},{"id":"kilo-auto/balanced","name":"Auto Balanced","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.325,"output":1.95,"reasoning":0,"cache_read":0.0325,"cache_write":0.40625},"display_name":"Auto Balanced","type":"chat"},{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"reka","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":58982},"cost":{"input":0.1,"output":0.2},"display_name":"Reka Flash 3","type":"chat"},{"id":"rekaai/reka-edge","name":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":14745},"cost":{"input":0.1,"output":0.1},"display_name":"Reka Edge","type":"chat"},{"id":"nvidia/nemotron-3.5-super-vl:free","name":"NVIDIA: Nemotron 3.5 Super VL (free)","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"display_name":"NVIDIA: Nemotron 3.5 Super VL (free)","type":"chat"},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.05,"output":0.2},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-content-safety:free","name":"NVIDIA: Nemotron 3.5 Content Safety (free)","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-content-safety","display_name":"NVIDIA: Nemotron 3.5 Content Safety (free)","type":"chat"},{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B A3B","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.025,"output":0.12,"cache_read":0.0125},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","name":"NVIDIA: Nemotron 3 Nano Omni (free)","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","display_name":"NVIDIA: Nemotron 3 Nano Omni (free)","type":"chat"},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.08,"output":0.45},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.1,"output":0.4,"cache_read":0.08},"display_name":"NVIDIA: Nemotron 3.5 Super VL","type":"chat"},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","name":"NVIDIA: Nemotron 3 Ultra (free)","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"NVIDIA: Nemotron 3 Ultra (free)","type":"chat"},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":182520},"cost":{"input":0.4,"output":1.76,"cache_read":0.08},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3-super-120b-a12b:free","name":"NVIDIA: Nemotron 3 Super (free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"NVIDIA: Nemotron 3 Super (free)","type":"chat"},{"id":"nvidia/nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":117964},"cost":{"input":0.2,"output":0.2},"canonical_model_id":"nvidia/nemotron-3.5-content-safety","display_name":"Nemotron 3.5 Content Safety","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-lightning:free","name":"NVIDIA: Nemotron 3.5 Lightning (free)","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"NVIDIA: Nemotron 3.5 Lightning (free)","type":"chat"},{"id":"xiaomi/mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.43,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.003,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","name":"MiMo-V2.6-Pro-UltraSpeed","description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":4.35,"output":8.7,"cache_read":0.036},"canonical_model_id":"xiaomi/mimo-v2.6-pro-ultraspeed","display_name":"MiMo-V2.6-Pro-UltraSpeed","type":"chat"},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.004,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.28,"cache_read":0.05},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2023-07-22","last_updated":"2023-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":6144,"output":5529},"cost":{"input":0.35,"output":0.65},"display_name":"ReMM SLERP 13B","type":"chat"},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2023-07-02","last_updated":"2023-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":3686},"cost":{"input":0.08,"output":0.11},"display_name":"MythoMax 13B","type":"chat"},{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":32768},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000192,"output":900172},"cost":{"input":0.2,"output":1.1},"display_name":"MiniMax: MiniMax-01","type":"chat"},{"id":"minimax/minimax-m2-her","name":"MiniMax-M2 Her","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":2048},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2-Her","display_name":"MiniMax-M2 Her","type":"chat"},{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":40000},"cost":{"input":0.4,"output":2.2},"display_name":"MiniMax: MiniMax M1","type":"chat"},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax-M2","type":"chat"},{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","family":"alpha","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2023-08-02","last_updated":"2023-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":6000},"cost":{"input":0.4,"output":0.75},"display_name":"Mancer: Weaver (alpha)","type":"chat"},{"id":"stepfun/step-5-preview","name":"Step 5 Preview","description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":1,"output":2.7,"cache_read":0.1},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"stepfun/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash","type":"chat"},{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":230400},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"dots-studio/dots-3-note-preview:free","name":"Dots Studio: Dots3-Note Preview (free)","description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":460800},"cost":{"input":0,"output":0},"display_name":"Dots Studio: Dots3-Note Preview (free)","type":"chat"},{"id":"inception/mercury-2.5","name":"Inception: Mercury 2.5","description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":260000,"output":65536},"cost":{"input":0.2,"output":0.75,"cache_read":0.02},"display_name":"Inception: Mercury 2.5","type":"chat"},{"id":"inception/mercury-2","name":"Inception: Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"display_name":"Inception: Mercury 2","type":"chat"},{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":0.06,"output":0.24},"display_name":"Amazon: Nova Lite 1.0","type":"chat"},{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.3,"output":2.5},"display_name":"Amazon: Nova 2 Lite","type":"chat"},{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":0.8,"output":3.2},"display_name":"Amazon: Nova Pro 1.0","type":"chat"},{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-31","last_updated":"2025-10-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":2.5,"output":12.5,"cache_read":0.625},"display_name":"Amazon: Nova Premier 1.0","type":"chat"},{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":5120},"cost":{"input":0.035,"output":0.14},"display_name":"Amazon: Nova Micro 1.0","type":"chat"},{"id":"relace/relace-search","name":"Relace: Relace Search","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":1,"output":3},"display_name":"Relace: Relace Search","type":"chat"},{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.85,"output":1.25},"display_name":"Relace: Relace Apply 3","type":"chat"},{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.8,"output":1.6,"cache_read":0.2},"display_name":"AionLabs: Aion-2.0","type":"chat"},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-02-04","last_updated":"2025-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":29491},"cost":{"input":0.8,"output":1.6},"display_name":"AionLabs: Aion-RP 1.0 (8B)","type":"chat"},{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion-3.0","description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":3,"output":6,"cache_read":0.75},"display_name":"AionLabs: Aion-3.0","type":"chat"},{"id":"aion-labs/aion-3.5","name":"AionLabs: Aion 3.5","description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":3,"output":6,"cache_read":0.75},"display_name":"AionLabs: Aion 3.5","type":"chat"},{"id":"aion-labs/aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.7,"output":1.4,"cache_read":0.18},"display_name":"AionLabs: Aion 3.5 Mini","type":"chat"},{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.7,"output":1.4,"cache_read":0.18},"display_name":"AionLabs: Aion-3.0-Mini","type":"chat"},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.09,"output":0.55},"display_name":"Qwen: Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.21,"output":1.9,"cache_read":0.1},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.425,"output":2.55,"cache_read":0.085,"cache_write":0.53125},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.195,"output":1.56},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-thinking","display_name":"Qwen3-Next 80B-A3B (Thinking)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.12,"output":0.8,"cache_read":0.07},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":1,"cache_read":0.1},"display_name":"Qwen: Qwen3 Coder 480B A35B","type":"chat"},{"id":"qwen/qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.08,"output":0.28},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.26,"output":0.78,"cache_read":0.052,"cache_write":0.325},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991808,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.07,"output":0.28},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"qwen/qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"alibaba/qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","type":"chat"},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.45,"output":3.5},"display_name":"Qwen: Qwen3 235B A22B Thinking 2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.26,"output":2.08},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.15,"output":1,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.09,"output":1.1},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct","type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.29,"output":1},"display_name":"Qwen: Qwen3 VL 30B A3B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.195,"output":0.975,"cache_read":0.039,"cache_write":0.24375},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-11","last_updated":"2024-11-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":29491},"cost":{"input":0.66,"output":1},"display_name":"Qwen2.5 Coder 32B Instruct","type":"chat"},{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.065,"output":0.26},"display_name":"Qwen: Qwen3.5-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.1,"output":0.15},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max-prime","name":"Qwen 3.8 Max Prime","description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","family":"qwen3.8-max","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":4,"output":12,"cache_read":0.5},"canonical_model_id":"alibaba/qwen3.8-max-prime","display_name":"Qwen 3.8 Max Prime","type":"chat"},{"id":"qwen/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.8,"cache_write":0.375},"display_name":"Qwen: Qwen3.5 Plus 2026-04-20","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.1625,"output":1.3},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.5},"canonical_model_id":"alibaba/qwen3-30b-a3b","display_name":"Qwen3 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.39,"output":2.34},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.25,"output":0.75,"cache_read":0.12},"display_name":"Qwen: Qwen3 VL 8B Instruct","type":"chat"},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0.09,"output":0.3},"display_name":"Qwen: Qwen3 30B A3B Instruct 2507","type":"chat"},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-02-01","last_updated":"2025-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":115200},"cost":{"input":0.8,"output":1,"cache_read":0.4},"display_name":"Qwen: Qwen2.5 VL 72B Instruct","type":"chat"},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-10-16","last_updated":"2024-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":29491},"cost":{"input":0.1,"output":0.2},"display_name":"Qwen: Qwen2.5 7B Instruct","type":"chat"},{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.26,"output":1.56},"display_name":"Qwen: Qwen3.5 Plus 2026-02-15","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.36,"output":0.4},"display_name":"Qwen2.5 72B Instruct","type":"chat"},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":2.7},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.325,"output":1.95,"cache_write":0.40625},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.24},"display_name":"Qwen: Qwen3 14B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"xingchen-agi/xing4.0-29b-a4b:free","name":"XingChen: Xing4.0 29B A4B (free)","description":"Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...","family":"agi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":235929},"cost":{"input":0,"output":0},"display_name":"XingChen: Xing4.0 29B A4B (free)","type":"chat"},{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.9,"output":1.9},"display_name":"Morph: Morph V3 Large","type":"chat"},{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":81920,"output":38000},"cost":{"input":0.8,"output":1.2},"display_name":"Morph: Morph V3 Fast","type":"chat"},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-image-2","name":"GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["image","text","pdf"],"output":["image","text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":8,"output":15,"cache_read":2},"canonical_model_id":"openai/gpt-5.4-image-2","display_name":"GPT-5.4 Image 2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-audio","name":"OpenAI: GPT Audio","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text","audio","pdf"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"display_name":"OpenAI: GPT Audio","type":"chat"},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5-turbo","type":"chat"},{"id":"openai/gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro ($$$$)","description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"OpenAI: GPT-6 Astra Pro ($$$$)","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":5,"output":15},"canonical_model_id":"openai/gpt-4o-2024-05-13","display_name":"GPT-4o (2024-05-13)","type":"chat"},{"id":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"display_name":"OpenAI: GPT-4o-mini (2024-07-18)","type":"chat"},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-05-05","last_updated":"2026-05-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"display_name":"OpenAI: GPT Chat Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-audio-mini","name":"OpenAI: GPT Audio Mini","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text","audio","pdf"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.6,"output":2.4},"display_name":"OpenAI: GPT Audio Mini","type":"chat"},{"id":"openai/gpt-5.6-sol-pro","name":"GPT-5.6 Sol","description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"canonical_model_id":"openai/gpt-5.2-pro","display_name":"GPT-5.2 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":4096},"cost":{"input":30,"output":60},"canonical_model_id":"openai/gpt-4","display_name":"GPT-4","type":"chat"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"canonical_model_id":"openai/o1","display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2023-09-28","last_updated":"2023-09-28","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":4095,"output":3685},"cost":{"input":1.5,"output":2},"display_name":"OpenAI: GPT-3.5 Turbo Instruct","type":"chat"},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-08-06","display_name":"GPT-4o (2024-08-06)","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.6-luna-pro","name":"GPT-5.6 Luna","description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat"},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-image-mini","name":"GPT-5 Image Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["pdf","image","text"],"output":["image","text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":2,"cache_read":0.25},"canonical_model_id":"openai/gpt-5-image-mini","display_name":"GPT-5 Image Mini","type":"chat"},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/o3-pro","name":"o3-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","pdf","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"canonical_model_id":"openai/o3-pro","display_name":"o3-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.018,"output":0.09,"cache_read":0.009},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B","type":"chat"},{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-02-12","last_updated":"2025-02-12","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"OpenAI: o3 Mini High","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2023-08-28","last_updated":"2023-08-28","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":3,"output":4},"display_name":"OpenAI: GPT-3.5 Turbo 16k","type":"chat"},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-10","last_updated":"2025-12-10","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"OpenAI: GPT-5.2 Chat","type":"chat"},{"id":"openai/gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"display_name":"OpenAI: GPT-6 Sol Pro","type":"chat"},{"id":"openai/gpt-5-image","name":"GPT-5 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text","pdf"],"output":["image","text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":10,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-5-image","display_name":"GPT-5 Image","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT-5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-11-20","display_name":"GPT-4o (2024-11-20)","type":"chat"},{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":4095,"output":3685},"cost":{"input":1,"output":2},"display_name":"OpenAI: GPT-3.5 Turbo (older v0613)","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-5.6-terra-pro","name":"GPT-5.6 Terra","description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"display_name":"OpenAI: GPT-6.1 Sol Pro","type":"chat"},{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"display_name":"OpenAI: o4 Mini High","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"display_name":"OpenAI: GPT-6 Luna Pro","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.03,"output":0.15,"cache_read":0.015},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3","name":"o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":150,"output":600},"canonical_model_id":"openai/o1-pro","display_name":"o1-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"microsoft/phi-4","name":"Microsoft: Phi 4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-01-10","last_updated":"2025-01-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":14745},"cost":{"input":0.056,"output":0.112},"display_name":"Microsoft: Phi 4","type":"chat"},{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-04-16","last_updated":"2024-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65535,"output":8000},"cost":{"input":0.62,"output":0.62},"display_name":"WizardLM-2 8x22B","type":"chat"}]},"venice":{"id":"venice","name":"Venice AI","doc":"https://docs.venice.ai","display_name":"Venice AI","models":[{"id":"qwen-3-8-2-4t-a95b","name":"Qwen 3.8 2.4T","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.3125},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen 3.8 2.4T","type":"chat"},{"id":"openai-gpt-56-luna","name":"GPT-5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat"},{"id":"grok-4-5","name":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":32000},"cost":{"input":2.27,"output":6.8,"cache_read":0.34,"tiers":[{"input":4.53,"output":13.6,"cache_read":0.68,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4.53,"output":13.6,"cache_read":0.68}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat"},{"id":"aion-labs-aion-3-5","name":"Aion 3.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":3.75,"output":7.5,"cache_read":0.9375},"display_name":"Aion 3.5","type":"chat"},{"id":"kimi-k3-fast-api","name":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 Fast","type":"chat"},{"id":"qwen3-6-27b","name":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.325,"output":3.25},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen 3.6 27B","type":"chat"},{"id":"hermes-3-llama-3.1-405b","name":"Hermes 3 Llama 3.1 405b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"hermes","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2025-09-25","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":3},"canonical_model_id":"nousresearch/hermes-3-llama-3.1-405b","display_name":"Hermes 3 Llama 3.1 405b","type":"chat"},{"id":"claude-opus-5-5-fast","name":"Claude Opus 5.5 Fast","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-26","last_updated":"2026-09-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":8,"output":40,"cache_read":0.4,"cache_write":10},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 Fast","type":"chat"},{"id":"kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-13","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.75,"output":3.5,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat"},{"id":"google-gemma-3-27b-it","name":"Google Gemma 3 27B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-04","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":16384},"cost":{"input":0.12,"output":0.2},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Google Gemma 3 27B Instruct","type":"chat"},{"id":"qwen-3-7-max","name":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-22","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.7,"output":8.05,"cache_read":0.27,"cache_write":3.35},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen 3.7 Max","type":"chat"},{"id":"qwen-3-8-max","name":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-22","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.5,"output":7.5,"cache_read":0.3125,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.8-max-preview","display_name":"Qwen 3.8 Max","type":"chat"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.13,"output":0.26,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"venice-uncensored-role-play","name":"Venice Role Play Uncensored","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-02-20","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.5,"output":2},"display_name":"Venice Role Play Uncensored","type":"chat"},{"id":"grok-build-0-1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat"},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen 3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.75},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen 3 235B A22B Instruct 2507","type":"chat"},{"id":"openai-gpt-6-luna","name":"GPT-6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3.75,"output":18.75,"cache_read":0.375},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai-gpt-54-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-27","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini","type":"chat"},{"id":"qwen-3-8-flash","name":"Qwen 3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.14,"output":0.49,"cache_read":0.014},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen 3.8 Flash","type":"chat"},{"id":"olafangensan-glm-4.7-flash-heretic","name":"GLM 4.7 Flash Heretic","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-02-04","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":24000},"cost":{"input":0.07,"output":0.4,"cache_read":0.035},"display_name":"GLM 4.7 Flash Heretic","type":"chat"},{"id":"xiaomi-mimo-v2-6-flash","name":"MiMo-V2.6-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.175,"output":0.35,"cache_read":0.00375},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"deepseek-v4-flash-0731-fast","name":"DeepSeek V4 Flash 0731 Fast","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-08-09","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.35,"output":0.7,"cache_read":0.0875},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-12-06","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":198000,"output":32768},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"zai-org-glm-5-2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat"},{"id":"claude-opus-4-8-fast","name":"Claude Opus 4.8 Fast","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"z-ai-glm-5-turbo","name":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-15","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM 5 Turbo","type":"chat"},{"id":"zai-org-glm-4.6","name":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2024-04-01","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":16384},"cost":{"input":0.43,"output":1.75,"cache_read":0.08},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"muse-wonder","name":"Muse Wonder","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-10-12","last_updated":"2026-10-15","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":5,"output":25,"cache_read":0.25},"display_name":"Muse Wonder","type":"chat"},{"id":"openai-gpt-54-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat"},{"id":"aion-labs-aion-3-0","name":"Aion 3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":3.75,"output":7.5,"cache_read":0.9375},"canonical_model_id":"aion-labs/aion-3.0","display_name":"Aion 3.0","type":"chat"},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-01-15","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":198000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-18","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"kimi-k2-5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2024-04","release_date":"2026-01-27","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.56,"output":3.5,"cache_read":0.22},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-08-29","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gemini-3-7-flash","name":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.9375,"output":4.6875,"cache_read":0.09375},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat"},{"id":"grok-4-20","name":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-03-12","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":1.42,"output":2.83,"cache_read":0.23,"tiers":[{"input":2.83,"output":5.67,"cache_read":0.45,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.83,"output":5.67,"cache_read":0.45}},"display_name":"Grok 4.20","type":"chat"},{"id":"openai-gpt-56-sol-pro","name":"GPT-5.6 Sol Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol Pro","type":"chat"},{"id":"seed-2-1-turbo","name":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-28","last_updated":"2026-07-24","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.625,"output":3.125,"cache_read":0.125},"canonical_model_id":"bytedance-seed/seed-2.1-turbo","display_name":"Seed 2.1 Turbo","type":"chat"},{"id":"z-ai-glm-5v-turbo","name":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32768},"cost":{"input":1.5,"output":5,"cache_read":0.3},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM 5V Turbo","type":"chat"},{"id":"openai-gpt-55-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat"},{"id":"qwen-3-7-plus","name":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":2,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":1.5,"output":6,"cache_read":0.15,"cache_write":1.875,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.5,"output":6,"cache_read":0.15,"cache_write":1.875}},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen 3.7 Plus","type":"chat"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen 3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2025-04-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.45,"output":3.5},"display_name":"Qwen 3 235B A22B Thinking 2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai-gpt-61-sol","name":"GPT-6.1 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"zai-org-glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM 4.7 Flash","type":"chat"},{"id":"openai-gpt-61-sol-ultrafast","name":"GPT-6.1 Sol Ultrafast","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-10-08","last_updated":"2026-10-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":12,"output":60,"cache_read":0.6,"cache_write":15,"tiers":[{"input":24,"output":90,"cache_read":1.2,"cache_write":30,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":24,"output":90,"cache_read":1.2,"cache_write":30}},"display_name":"GPT-6.1 Sol Ultrafast","type":"chat"},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-23","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai-gpt-6-astra","name":"GPT-6 Astra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-05","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat"},{"id":"minimax-m27","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":32768},"cost":{"input":0.375,"output":1.5,"cache_read":0.06875},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7","type":"chat"},{"id":"mercury-2-5","name":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-08","last_updated":"2026-09-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":260000,"output":65536},"cost":{"input":0.25,"output":0.9375,"cache_read":0.025},"canonical_model_id":"inception/mercury-2.5","display_name":"Mercury 2.5","type":"chat"},{"id":"qwen3-next-80b","name":"Qwen 3 Next 80b","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2025-04-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.35,"output":1.9},"display_name":"Qwen 3 Next 80b","type":"chat"},{"id":"minimax-m25","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":32768},"cost":{"input":0.27,"output":0.95,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-6-35b-a3b","name":"Qwen 3.6 35B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-20","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.1,"output":1},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen 3.6 35B A3B","type":"chat"},{"id":"grok-4-20-multi-agent","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"release_date":"2026-03-12","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":1.42,"output":2.83,"cache_read":0.23,"tiers":[{"input":2.83,"output":5.67,"cache_read":0.45,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.83,"output":5.67,"cache_read":0.45}},"display_name":"Grok 4.20 Multi-Agent","type":"chat"},{"id":"zai-org-glm-4.7","name":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-24","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":16384},"cost":{"input":0.55,"output":2.65,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-5-9b","name":"Qwen 3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.1,"output":0.15},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen 3.5 9B","type":"chat"},{"id":"qwen3-vl-235b-a22b","name":"Qwen3 VL 235B","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"release_date":"2026-01-16","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.21,"output":1.9,"cache_read":0.1},"display_name":"Qwen3 VL 235B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-10","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"qwen3-5-35b-a3b","name":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-25","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.15,"output":1,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen 3.5 35B A3B","type":"chat"},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":1.65,"output":4.95,"cache_read":0.165},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai-gpt-56-terra","name":"GPT-5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat"},{"id":"llama-3.3-70b","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"release_date":"2025-04-06","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.7,"output":2.8},"display_name":"Llama 3.3 70B","type":"chat"},{"id":"openai-gpt-4o-mini-2024-07-18","name":"GPT-4o Mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2026-02-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o Mini","type":"chat"},{"id":"mistral-small-3-2-24b-instruct","name":"Mistral Small 3.2 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2026-01-15","last_updated":"2026-06-11","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.09375,"output":0.25},"canonical_model_id":"mistral/mistral-small-3.2-24b-instruct","display_name":"Mistral Small 3.2 24B Instruct","type":"chat"},{"id":"inkling","name":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":1.25,"output":5.0625,"cache_read":0.2125},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"z-ai-glm-5-3","name":"GLM 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-18","last_updated":"2026-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.75,"output":5.5,"cache_read":0.325},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat"},{"id":"google-gemma-4-26b-a4b-it","name":"Google Gemma 4 26B A4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.13,"output":0.4,"cache_read":0.05},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Google Gemma 4 26B A4B Instruct","type":"chat"},{"id":"kimi-k2-6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-20","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.75,"output":3.5,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai-gpt-6-astra-pro","name":"GPT-6 Astra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-05","last_updated":"2026-09-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"display_name":"GPT-6 Astra Pro","type":"chat"},{"id":"openai-gpt-54","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":131072},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat"},{"id":"gemma-4-uncensored","name":"Gemma 4 Uncensored","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-04-13","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.1625,"output":0.5},"display_name":"Gemma 4 Uncensored","type":"chat"},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"abliteration-abliterated-model-large-v2","name":"Abliterated Large V2","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":3,"output":5,"cache_read":0.3},"display_name":"Abliterated Large V2","type":"chat"},{"id":"minimax-m3-preview","name":"MiniMax M3 Preview","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"release_date":"2026-06-12","last_updated":"2026-06-13","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax M3 Preview","type":"chat"},{"id":"openai-gpt-oss-120b","name":"OpenAI GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-06","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.07,"output":0.3},"canonical_model_id":"openai/gpt-oss-120b","display_name":"OpenAI GPT OSS 120B","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-29","last_updated":"2026-07-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.0075},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.9375,"output":4.6875,"cache_read":0.09375},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat"},{"id":"qwen-3-6-plus","name":"Qwen 3.6 Plus Uncensored","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-06","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.625,"output":3.75,"cache_read":0.0625,"cache_write":0.78,"tiers":[{"input":2.5,"output":7.5,"cache_read":0.0625,"cache_write":0.78,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2.5,"output":7.5,"cache_read":0.0625,"cache_write":0.78}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen 3.6 Plus Uncensored","type":"chat"},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"openai-gpt-6-sol","name":"GPT-6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"qwen-3-8-27b","name":"Qwen 3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-17","last_updated":"2026-08-18","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":3.2},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen 3.8 27B","type":"chat"},{"id":"openai-gpt-53-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat"},{"id":"aion-labs-aion-3-0-mini","name":"Aion 3.0 Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":0.875,"output":1.75,"cache_read":0.225},"canonical_model_id":"aion-labs/aion-3.0-mini","display_name":"Aion 3.0 Mini","type":"chat"},{"id":"grok-4-3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-18","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":1.42,"output":2.83,"cache_read":0.23,"tiers":[{"input":2.83,"output":5.67,"cache_read":0.45,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.83,"output":5.67,"cache_read":0.45}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat"},{"id":"aion-labs-aion-3-5-mini","name":"Aion 3.5 Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.875,"output":1.75,"cache_read":0.225},"display_name":"Aion 3.5 Mini","type":"chat"},{"id":"openai-gpt-56-terra-pro","name":"GPT-5.6 Terra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra Pro","type":"chat"},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-19","last_updated":"2026-06-11","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.7,"output":3.75,"cache_read":0.07},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-20","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.3125,"output":0.9375,"cache_read":0.03125},"canonical_model_id":"inception/mercury-2","display_name":"Mercury 2","type":"chat"},{"id":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.0075},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"grok-4-6","name":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-10","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":200000},"cost":{"input":2.27,"output":6.8,"cache_read":0.57,"tiers":[{"input":4.53,"output":13.6,"cache_read":1.13,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4.53,"output":13.6,"cache_read":1.13}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat"},{"id":"zai-org-glm-5-1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":80000},"cost":{"input":1.54,"output":4.84,"cache_read":0.286},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi-mimo-v2-5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-06-11","last_updated":"2026-06-11","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2,"cache_read":0.08},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"openai-gpt-4o-2024-11-20","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2026-02-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-11-20","display_name":"GPT-4o","type":"chat"},{"id":"openai-gpt-52","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-13","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":272000,"output":65536},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat"},{"id":"gemini-3-6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-09","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.9375,"output":4.6875,"cache_read":0.09375},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat"},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-06-11","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2.5,"output":15,"cache_read":0.5,"cache_write":0.5,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":0.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":0.5}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":1.65,"output":3.301,"cache_read":0.33},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-5-fast","name":"Claude Opus 5 Fast","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-23","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 Fast","type":"chat"},{"id":"openai-gpt-55","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":131072},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat"},{"id":"openai-gpt-56-sol","name":"GPT-5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat"},{"id":"qwen3-coder-480b-a35b-instruct-turbo","name":"Qwen 3 Coder 480B Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-01-27","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"display_name":"Qwen 3 Coder 480B Turbo","type":"chat"},{"id":"z-ai-glm-5-3-flash","name":"GLM 5.3 Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat"},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-26","last_updated":"2026-09-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"zai-org-glm-5","name":"GLM 5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":32000},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-4-7","name":"Grok 4.7","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-16","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":200000},"cost":{"input":2.27,"output":6.8,"cache_read":0.57,"tiers":[{"input":4.53,"output":13.6,"cache_read":1.13,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4.53,"output":13.6,"cache_read":1.13}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-04","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":32768},"cost":{"input":0.33,"output":0.48,"cache_read":0.16},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-5-flash-lite","name":"Gemini 3.5 Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-09","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.375,"output":3.125,"cache_read":0.0375},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash-Lite","type":"chat"},{"id":"hy4-preview","name":"Hy4 Preview","description":"Preview model for early access evaluation, prototyping, and compatibility testing","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":1.0425,"output":3.12625,"cache_read":0.0525},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-22","last_updated":"2026-06-11","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.55,"output":9.45,"cache_read":0.155,"cache_write":0.086},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat"},{"id":"google-gemma-4-31b-it","name":"Google Gemma 4 31B Instruct","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-03","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.12,"output":0.36,"cache_read":0.09},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Google Gemma 4 31B Instruct","type":"chat"},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"venice-uncensored-1-2","name":"Venice Uncensored 1.2","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-04-01","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.9},"display_name":"Venice Uncensored 1.2","type":"chat"},{"id":"nvidia-nemotron-3-5-super-vl-120b-a12b","name":"NVIDIA Nemotron 3.5 Super VL 120B","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.25,"output":1.25,"cache_read":0.125},"canonical_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","display_name":"NVIDIA Nemotron 3.5 Super VL 120B","type":"chat"},{"id":"qwen3-5-397b-a17b","name":"Qwen 3.5 397B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.75,"output":4.5},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen 3.5 397B","type":"chat"},{"id":"llama-3.2-3b","name":"Llama 3.2 3B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-10-03","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"meta/llama-3.2-3b","display_name":"Llama 3.2 3B","type":"chat"},{"id":"openai-gpt-56-luna-pro","name":"GPT-5.6 Luna Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna Pro","type":"chat"},{"id":"nvidia-nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.625,"output":3.125,"cache_read":0.1875},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"NVIDIA Nemotron 3 Ultra","type":"chat"},{"id":"muse-spark-open","name":"Muse Spark Open","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.5625,"output":5.3125,"cache_read":0.1875},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Gemini multimodal model for text, image, audio, video, and document tasks","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-14","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":12.5,"cache_read":0.125},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash 0423","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.138,"output":0.275,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash 0423","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"nvidia-nemotron-3-nano-30b-a3b","name":"NVIDIA Nemotron 3 Nano 30B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.075,"output":0.3},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"NVIDIA Nemotron 3 Nano 30B","type":"chat"}]},"alibaba-token-plan-cn":{"id":"alibaba-token-plan-cn","api":"https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1","name":"Alibaba Token Plan (China)","doc":"https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview","display_name":"Alibaba Token Plan (China)","models":[{"id":"happyhorse-1.1-r2v","name":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"HappyHorse 1.1 Reference-to-Video","type":"chat"},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"happyhorse-1.1-t2v","name":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"HappyHorse 1.1 Text-to-Video","type":"chat"},{"id":"qwen-image-2.0","name":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen Image 2.0","type":"image-generation"},{"id":"glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-max-preview","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.8-max-preview","display_name":"Qwen3.8 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen-image-2.0-pro","name":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen Image 2.0 Pro","type":"image-generation"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"wan2.7-image","name":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Wan2.7 Image","type":"image-generation"},{"id":"wan2.7-image-pro","name":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Wan2.7 Image Pro","type":"image-generation"},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"happyhorse-1.1-i2v","name":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"HappyHorse 1.1 Image-to-Video","type":"chat"},{"id":"qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"input":196601,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-03","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0,"output":0},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"ai21":{"id":"ai21","api":"https://api.ai21.com/studio/v1","name":"AI21 Labs","doc":"https://docs.ai21.com/docs/jamba-foundation-models","display_name":"AI21 Labs","models":[{"id":"jamba-large","name":"Jamba Large","description":"AI21's hybrid SSM-Transformer long-context model for enterprise agents and grounded generation","family":"jamba","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-22","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":2,"output":8},"canonical_model_id":"ai21/jamba-large","display_name":"Jamba Large","type":"chat"},{"id":"jamba-mini","name":"Jamba Mini","description":"AI21's efficient, lightweight hybrid SSM-Transformer model for a wide range of tasks","family":"jamba","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-22","release_date":"2026-01-01","last_updated":"2026-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.2,"output":0.4},"canonical_model_id":"ai21/jamba-mini","display_name":"Jamba Mini","type":"chat"}]},"commandcode":{"id":"commandcode","api":"https://api.commandcode.ai/provider/v1","name":"CommandCode","doc":"https://commandcode.ai/docs/provider","display_name":"CommandCode","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":0},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2,"output":8,"cache_read":0.5,"cache_write":0},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":0},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4.1-flash-fast","name":"DeepSeek V4.1 Flash Fast","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.16,"output":0.58,"cache_read":0.016},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash Fast","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash-fast","name":"DeepSeek V4 Flash Fast","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.28,"output":0.56,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash Fast","type":"chat"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"tencent/hy3-paid","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat"},{"id":"tencent/hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flashx","name":"GLM-5.3-FlashX","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.37,"output":1.25,"cache_read":0.075},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-FlashX","type":"chat"},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.5,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat"},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 (Contributor)","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2 (Contributor)","type":"chat"},{"id":"meta/muse-wonder-1.0","name":"Muse Wonder","description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"meta/muse-wonder-1.0","display_name":"Muse Wonder","type":"chat"},{"id":"meta/muse-spark-1.3-contributor","name":"Muse Spark 1.3 (Contributor)","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3 (Contributor)","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.08334},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.4,"output":3,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"Qwen/Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3.8-Max-0902","name":"Qwen3.8 Max 0902","description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"Qwen/Qwen3.8-Flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.16,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3.8-Omni-Flash","name":"Qwen3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","type":"chat"},{"id":"xai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"inclusionai/ling-3.1-flash:free","name":"Ling 3.1 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"inclusionai/ling-3.1-flash","display_name":"Ling 3.1 Flash","type":"chat"},{"id":"moonshotai/Kimi-K2.7-Code-Highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.2-Fast","name":"GLM-5.2-Fast","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":10.25,"cache_read":0.5},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2-Fast","type":"chat"},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"stepfun/Step-3.7-Flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"stepfun/Step-5-Preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":1,"output":2.7,"cache_read":0.05},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"stepfun/Step-3.5-Flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.09,"output":0.3,"cache_read":0.02},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash","type":"chat"},{"id":"mistral/mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":262144},"cost":{"input":1.36,"output":4.18,"cache_read":0.14},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"}]},"lowrouter":{"id":"lowrouter","api":"https://api.lowrouter.ai/v1","name":"LowRouter","doc":"https://lowrouter.ai/docs/models/available","display_name":"LowRouter","models":[{"id":"auto/mistralai/ministral-8b-2512","name":"Ministral 3 8B","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1569,"output":0.1569,"cache_read":0.0157},"canonical_model_id":"mistral/ministral-3-8b-instruct-2512","display_name":"Ministral 3 8B","type":"chat"},{"id":"auto/mistralai/mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":262144},"status":"beta","cost":{"input":0.7112,"output":2.1859,"cache_read":0.0732},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"auto/mistralai/mistral-medium-3.5","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5688,"output":7.8442,"cache_read":0.1569},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"auto/mistralai/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.1569,"output":0.6275,"cache_read":0.0157},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"auto/mistralai/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5229,"output":1.5688,"cache_read":0.0523},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"auto/mistralai/ministral-14b-2512","name":"Ministral 3 14B","description":"Open vision-language model for efficient local deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2092,"output":0.2092,"cache_read":0.0209},"canonical_model_id":"mistral/ministral-3-14b-instruct-2512","display_name":"Ministral 3 14B","type":"chat"},{"id":"auto/mistralai/ministral-3b-2512","name":"Ministral 3 3B","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1046,"output":0.1046,"cache_read":0.0105},"canonical_model_id":"mistral/ministral-3-3b-instruct-2512","display_name":"Ministral 3 3B","type":"chat"},{"id":"auto/mistralai/codestral-2508","name":"Codestral 25.08","description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.3138,"output":0.9413,"cache_read":0.0314},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 25.08","type":"chat"},{"id":"auto/openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.18,"output":0.73},"canonical_model_id":"openai/gpt-oss-safeguard-120b","display_name":"GPT OSS Safeguard 120B","type":"chat"},{"id":"auto/openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"auto/openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"auto/openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"auto/openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"auto/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.113,"output":0.4745},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"auto/openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.08,"output":0.24},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B","type":"chat"},{"id":"auto/openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"auto/openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"auto/openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"auto/openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1695,"output":0.6779},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"auto/openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto/openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"reflection":{"id":"reflection","api":"https://api.reflection.ai/openai/v1","name":"Reflection","doc":"https://developers.reflection.ai/models","display_name":"Reflection","models":[{"id":"Beam-1.0-501B-A23B","name":"Beam 1.0 501B A23B","description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-06-30","release_date":"2026-10-05","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"reflection/beam-1.0-501b-a23b","display_name":"Beam 1.0 501B A23B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"inference":{"id":"inference","api":"https://inference.net/v1","name":"Inference","doc":"https://inference.net/models","display_name":"Inference","models":[{"id":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.025,"output":0.025},"display_name":"Llama 3.1 8B Instruct","type":"chat"},{"id":"meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.055,"output":0.055},"display_name":"Llama 3.2 11B Vision Instruct","type":"chat"},{"id":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.01,"output":0.01},"display_name":"Llama 3.2 1B Instruct","type":"chat"},{"id":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.02,"output":0.02},"display_name":"Llama 3.2 3B Instruct","type":"chat"},{"id":"google/gemma-3","name":"Google Gemma 3","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":125000,"output":4096},"cost":{"input":0.15,"output":0.3},"display_name":"Google Gemma 3","type":"chat"},{"id":"osmosis/osmosis-structure-0.6b","name":"Osmosis Structure 0.6B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"osmosis","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4000,"output":2048},"cost":{"input":0.1,"output":0.5},"display_name":"Osmosis Structure 0.6B","type":"chat"},{"id":"mistral/mistral-nemo-12b-instruct","name":"Mistral Nemo 12B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.038,"output":0.1},"display_name":"Mistral Nemo 12B Instruct","type":"chat"},{"id":"qwen/qwen3-embedding-4b","name":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":2048},"cost":{"input":0.01,"output":0},"display_name":"Qwen 3 Embedding 4B","type":"embedding"},{"id":"qwen/qwen-2.5-7b-vision-instruct","name":"Qwen 2.5 7B Vision Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":125000,"output":4096},"cost":{"input":0.2,"output":0.2},"display_name":"Qwen 2.5 7B Vision Instruct","type":"chat"}]},"iflowcn":{"id":"iflowcn","api":"https://apis.iflow.cn/v1","name":"iFlow","doc":"https://platform.iflow.cn/en/docs","display_name":"iFlow","models":[{"id":"qwen3-vl-plus","name":"Qwen3-VL-Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0,"output":0},"display_name":"Qwen3-VL-Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2025-11-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0,"output":0},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3-32b","name":"Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"display_name":"Qwen3-32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-max","name":"Qwen3-Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0,"output":0},"display_name":"Qwen3-Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v3","name":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"display_name":"DeepSeek-V3","type":"chat"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen3-235B-A22B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"display_name":"Qwen3-235B-A22B-Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-max-preview","name":"Qwen3-Max-Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0,"output":0},"display_name":"Qwen3-Max-Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-coder-plus","name":"Qwen3-Coder-Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"display_name":"Qwen3-Coder-Plus","type":"chat"},{"id":"qwen3-235b-a22b-instruct","name":"Qwen3-235B-A22B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"display_name":"Qwen3-235B-A22B-Instruct","type":"chat"},{"id":"kimi-k2-0905","name":"Kimi-K2-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"display_name":"Kimi-K2-0905","type":"chat"},{"id":"kimi-k2","name":"Kimi-K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0,"output":0},"display_name":"Kimi-K2","type":"chat"},{"id":"qwen3-235b","name":"Qwen3-235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"display_name":"Qwen3-235B-A22B","type":"chat"},{"id":"deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v3.2","name":"DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":0,"output":0},"display_name":"DeepSeek-V3.2-Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"minimax-cn-coding-plan":{"id":"minimax-cn-coding-plan","api":"https://api.minimax.cn/anthropic/v1","name":"MiniMax Token Plan (minimax.cn)","doc":"https://platform.minimaxi.com/docs/token-plan/intro","display_name":"MiniMax Token Plan (minimax.cn)","models":[{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M3.1-Flash-Preview","name":"MiniMax-M3.1-Flash-Preview","description":"Frontier multimodal coding model with 1M context window and tunable thinking depth","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-27","last_updated":"2026-09-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":512000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"minimax/MiniMax-M3.1-Flash-Preview","display_name":"MiniMax-M3.1-Flash-Preview","type":"chat"},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0},"display_name":"MiniMax-M2","type":"chat"},{"id":"MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.5-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"thinkingmachines":{"id":"thinkingmachines","api":"https://tinker.thinkingmachines.dev/services/tinker-prod/anthropic/api/v1","name":"Thinking Machines","doc":"https://tinker-docs.thinkingmachines.ai/tinker/compatible-apis/anthropic/","display_name":"Thinking Machines","models":[{"id":"thinkingmachines/Inkling:peft:262144","name":"Inkling (256K)","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":3.74,"output":9.36,"cache_read":0.748},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling (256K)","type":"chat"},{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":1.87,"output":4.68,"cache_read":0.374},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"}]},"stepfun-step-plan":{"id":"stepfun-step-plan","api":"https://api.stepfun.com/step_plan/v1","name":"StepFun Step Plan (China)","doc":"https://platform.stepfun.com/docs/zh/step-plan/integrations/reasoning-api","display_name":"StepFun Step Plan (China)","models":[{"id":"step-5-preview","name":"Step 5 Preview","description":"StepFun frontier model for large-scale agent applications, coding, and knowledge work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":384000},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","metadata":{"source":"public-provider-conf-template","lifecycle":"preview","notes":["Official maximum input and output are both 1M tokens and max_tokens defaults to INF; 384000 is recorded as a conservative default output ceiling.","Step Plan usage is billed as monthly subscription Credits rather than per-token prices."]},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["low","medium","high"],"mode":"effort","effort":"medium"}},"temperature":true,"type":"chat","vision":true},{"id":"step-router-v1","name":"Step Router v1","description":"StepFun routing model that dispatches requests to the appropriate Step model.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":256000},"display_name":"Step Router v1","type":"chat"},{"id":"step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"canonical_model_id":"stepfun/step-3.5-flash-2603","display_name":"Step 3.5 Flash 2603","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"}]},"melious":{"id":"melious","api":"https://api.melious.ai/v1","name":"Melious","doc":"https://melious.ai/docs/reference/models","display_name":"Melious","models":[{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.11592,"output":0.46368,"cache_read":0.023184},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.11592,"output":0.2898,"cache_read":0.023184},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3.1878,"output":15.939,"cache_read":0.788256},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131072},"cost":{"input":1.10124,"output":3.36168,"cache_read":0.266616},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.23184,"output":1.1592,"cache_read":0.011592},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.81144,"output":4.0572,"cache_read":0.266616},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.5796,"output":2.95596,"cache_read":0.139104},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131072},"cost":{"input":1.50696,"output":4.6368,"cache_read":0.370944},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-r1-0528","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":32768},"cost":{"input":0.69552,"output":2.78208,"cache_read":0.185472},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":64000},"cost":{"input":0.34776,"output":0.5796,"cache_read":0.092736},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.1592,"output":3.4776,"cache_read":0.23184},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.81144,"output":3.4776,"cache_read":0.220248},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"berget":{"id":"berget","api":"https://api.berget.ai/v1","name":"Berget.AI","doc":"https://api.berget.ai","display_name":"Berget.AI","models":[{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["audio","image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.275,"output":0.55},"display_name":"Gemma 4 31B Instruct","type":"chat"},{"id":"Qwen/Qwen3.8-27B-FP8","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.46,"output":3.48},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral Small 3.2 24B Instruct 2506","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":8192},"cost":{"input":0.33,"output":0.33},"display_name":"Mistral Small 3.2 24B Instruct 2506","type":"chat"},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":327680,"output":32768},"cost":{"input":3,"output":15},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":32768},"cost":{"input":1.54,"output":4.84},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-09-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":0.29,"output":0.58},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"snowflake-cortex":{"id":"snowflake-cortex","api":"https://${SNOWFLAKE_ACCOUNT}.snowflakecomputing.com/api/v2/cortex/v1","name":"Snowflake Cortex","doc":"https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api","display_name":"Snowflake Cortex","models":[{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"openai-gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat"},{"id":"claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"openai-gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"input":272000,"output":8192},"status":"beta","canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat"},{"id":"openai-gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"input":272000,"output":8192},"status":"beta","canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat"},{"id":"openai-gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-large2","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"canonical_model_id":"mistral/mistral-large-latest","display_name":"Mistral Large (latest)","type":"chat"},{"id":"openai-gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat"},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai-gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat"},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"openai-gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat"},{"id":"openai-gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"input":272000,"output":8192},"status":"beta","canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat"},{"id":"deepseek-r1","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":16384},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"openai-gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"input":272000,"output":8192},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat"},{"id":"snowflake-llama3.3-70b","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"openai-gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat"},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gemini-3.1-pro","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"openai-gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat"}]},"sarvam":{"id":"sarvam","api":"https://api.sarvam.ai/v1","name":"Sarvam AI","doc":"https://docs.sarvam.ai/api-reference-docs/getting-started/models","display_name":"Sarvam AI","models":[{"id":"sarvam-30b","name":"Sarvam-30B","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","family":"sarvam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":[null,"low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-18","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"display_name":"Sarvam-30B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"sarvam-105b","name":"Sarvam-105B","description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":[null,"low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-18","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"display_name":"Sarvam-105B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"nova":{"id":"nova","api":"https://api.nova.amazon.com/v1","name":"Nova","doc":"https://nova.amazon.com/dev/documentation","display_name":"Nova","models":[{"id":"nova-2-pro-v1","name":"Nova 2 Pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2026-01-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"reasoning":0},"display_name":"Nova 2 Pro","type":"chat"},{"id":"nova-2-lite-v1","name":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"reasoning":0},"display_name":"Nova 2 Lite","type":"chat"}]},"abacus":{"id":"abacus","api":"https://routellm.abacus.ai/v1","name":"Abacus","doc":"https://abacus.ai/help/api","display_name":"Abacus","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-11-17","last_updated":"2025-11-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":16384},"cost":{"input":0.2,"output":0.5},"display_name":"Grok 4.1 Fast (Non-Reasoning)","type":"chat"},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.5,"output":7.5},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-image-preview","name":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image-preview","display_name":"Nano Banana 2 Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Nano Banana","type":"image-generation"},{"id":"gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5-codex","display_name":"GPT-5-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-3-7-sonnet-20250219","name":"Claude Sonnet 3.7","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"display_name":"Claude Sonnet 3.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"qwen-2.5-coder-32b","name":"Qwen 2.5 Coder 32B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-11-11","last_updated":"2024-11-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.79,"output":0.79},"display_name":"Qwen 2.5 Coder 32B","type":"chat"},{"id":"o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.18},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-chat-latest","name":"GPT-5.2 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2026-01-01","last_updated":"2026-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14},"display_name":"GPT-5.2 Chat Latest","type":"chat"},{"id":"gpt-5.1-chat-latest","name":"GPT-5.1 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10},"display_name":"GPT-5.1 Chat Latest","type":"chat"},{"id":"qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":1.2,"output":6},"display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-4-20250514","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"display_name":"Claude Opus 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"kimi-k2-turbo-preview","name":"Kimi K2 Turbo Preview","description":"Fast Kimi model for responsive chat, coding help, and agent loops","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"cost":{"input":0.15,"output":8},"display_name":"Kimi K2 Turbo Preview","type":"chat"},{"id":"grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4-fast-non-reasoning","name":"Grok 4 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":16384},"cost":{"input":0.2,"output":0.5},"display_name":"Grok 4 Fast (Non-Reasoning)","type":"chat"},{"id":"claude-opus-4-1-20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"gemini-3-pro-image-preview","name":"Nano Banana Pro Preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2},"canonical_model_id":"google/gemini-3-pro-image-preview","display_name":"Nano Banana Pro Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":32768},"cost":{"input":2,"output":6},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"llama-3.3-70b-versatile","name":"Llama 3.3 70B Versatile","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.59,"output":0.79},"display_name":"Llama 3.3 70B Versatile","type":"chat"},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":3,"cache_read":0.2},"canonical_model_id":"xiaomi/mimo-v2-pro","display_name":"MiMo-V2-Pro","type":"chat"},{"id":"gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":40},"canonical_model_id":"openai/o3-pro","display_name":"o3-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10},"display_name":"GPT-5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"grok-code-fast-1","name":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":0.2,"output":1.5},"display_name":"Grok Code Fast 1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5.3-codex-xhigh","name":"GPT-5.3 Codex XHigh","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14},"display_name":"GPT-5.3 Codex XHigh","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"display_name":"GPT-4o (2024-11-20)","type":"chat"},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-5.3-chat-latest","name":"GPT-5.3 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14},"display_name":"GPT-5.3 Chat Latest","type":"chat"},{"id":"claude-sonnet-4-20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"display_name":"Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":32768},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1},"display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"route-llm","name":"RouteLLM","description":"RouteLLM routes prompts to an appropriate Abacus-backed text-generation model","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2026-07-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":3,"output":15},"display_name":"RouteLLM","type":"chat"},{"id":"grok-4-0709","name":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":3,"output":15},"display_name":"Grok 4","type":"chat"},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.55,"output":1.66},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"meta-llama/Meta-Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.59,"output":0.79},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"meta-llama/Meta-Llama-3.1-8B-Instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.02,"output":0.05},"display_name":"Llama 3.1 8B Instruct","type":"chat"},{"id":"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","name":"Llama 3.1 405B Instruct Turbo","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":3.5,"output":3.5},"display_name":"Llama 3.1 405B Instruct Turbo","type":"chat"},{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8192},"cost":{"input":0.14,"output":0.59},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct","type":"chat"},{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":3.74,"output":9.36,"cache_read":0.748},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"Qwen/QwQ-32B","name":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2024-11-28","last_updated":"2024-11-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.4,"output":0.4},"display_name":"QwQ 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.13,"output":0.6},"display_name":"Qwen3 235B A22B Instruct","type":"chat"},{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen 2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.11,"output":0.38},"display_name":"Qwen 2.5 72B Instruct","type":"chat"},{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.09,"output":0.29},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.29,"output":1.2},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3-Coder 480B-A35B Instruct","type":"chat"},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.32,"output":3.2},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":3,"output":7},"display_name":"DeepSeek R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":1.74,"output":3.48,"cache_read":0.15},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-15","last_updated":"2025-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.27,"output":0.4},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.27,"output":1},"display_name":"DeepSeek V3.1 Terminus","type":"chat"},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":2.2},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":96000},"cost":{"input":0.6,"output":2.2},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.08,"output":0.44},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"novita-ai":{"id":"novita-ai","api":"https://api.novita.ai/openai","name":"Novita AI","doc":"https://novita.ai/docs/guides/introduction","display_name":"Novita AI","models":[{"id":"baai/bge-m3","type":"embedding","name":"BGE M3","description":"Multilingual embedding model combining dense, sparse, and multi-vector retrieval","family":"bge","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-01-30","last_updated":"2024-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.01,"output":0},"canonical_model_id":"baai/bge-m3","display_name":"BGE M3"},{"id":"baai/bge-reranker-v2-m3","type":"rerank","name":"BGE Reranker V2 M3","description":"Lightweight multilingual cross-encoder that scores query-document relevance","family":"bge","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-03-15","last_updated":"2024-03-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8192},"cost":{"input":0.01,"output":0},"canonical_model_id":"baai/bge-reranker-v2-m3","display_name":"BGE Reranker V2 M3"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.44,"output":1.32,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-r1-0528-qwen3-8b","name":"DeepSeek R1 0528 Qwen3 8B","description":"DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-05-29","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.06,"output":0.09},"canonical_model_id":"deepseek/deepseek-r1-0528-qwen3-8b","display_name":"DeepSeek R1 0528 Qwen3 8B","type":"chat"},{"id":"deepseek/deepseek-ocr-2","name":"DeepSeek OCR 2","description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.03,"output":0.03},"canonical_model_id":"deepseek/deepseek-ocr-2","display_name":"DeepSeek OCR 2","type":"chat"},{"id":"deepseek/deepseek-r1-turbo","name":"DeepSeek R1 (Turbo)","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16000},"cost":{"input":0.7,"output":2.5},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek R1 (Turbo)","type":"chat"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek_v3","name":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16000},"cost":{"input":0.89,"output":0.89},"canonical_model_id":"deepseek/deepseek-v3","display_name":"DeepSeek-V3","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":1.6,"output":3.2,"cache_read":0.135},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528","description":"May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.7,"output":2.5,"cache_read":0.35},"canonical_model_id":"deepseek/deepseek-r1-0528","display_name":"DeepSeek R1 0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":262144},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"tencent/hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8192},"cost":{"input":0.27,"output":0.85},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct","type":"chat"},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":12288,"output":12288},"cost":{"input":0.135,"output":0.4},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.02,"output":0.05},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama-3.1-8B-Instruct","type":"chat"},{"id":"meta-llama/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":32000},"cost":{"input":0.02,"output":0.02},"canonical_model_id":"meta/llama-3.2-1b-instruct","display_name":"Llama 3.2 1B Instruct","type":"chat"},{"id":"meta-llama/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.18,"output":0.59},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B Instruct","type":"chat"},{"id":"nousresearch/hermes-2-pro-llama-3-8b","name":"Hermes 2 Pro Llama 3 8B","description":"Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-04-30","last_updated":"2024-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.14,"output":0.14},"canonical_model_id":"nousresearch/hermes-2-pro-llama-3-8b","display_name":"Hermes 2 Pro Llama 3 8B","type":"chat"},{"id":"xiaomimimo/mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomimimo/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.168,"output":0.336,"cache_read":0.0034},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomimimo/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.522,"output":1.044,"cache_read":0.0043},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomimimo/mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"baidu/ernie-4.5-21B-a3b","name":"ERNIE 4.5 21B A3B","description":"Open ERNIE text MoE with 21B total and 3B active parameters","family":"ernie","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":120000,"output":8000},"cost":{"input":0.07,"output":0.28},"canonical_model_id":"baidu/ernie-4.5-21b-a3b","display_name":"ERNIE 4.5 21B A3B","type":"chat"},{"id":"baidu/cobuddy","name":"CoBuddy","description":"Baidu Qianfan model optimized for code generation and tool-using coding agents","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-05-06","last_updated":"2026-05-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.28,"output":1.13,"cache_read":0.07},"canonical_model_id":"baidu/cobuddy","display_name":"CoBuddy","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":98304,"output":16384},"cost":{"input":0.119,"output":0.2},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT","type":"chat"},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.13,"output":0.4},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.05,"output":0.1},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT","type":"chat"},{"id":"minimaxai/minimax-m1-80k","name":"MiniMax M1 80K","description":"Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":40000},"cost":{"input":0.55,"output":2.2},"canonical_model_id":"minimax/minimax-m1-80k","display_name":"MiniMax M1 80K","type":"chat"},{"id":"inclusionai/ling-3.0-flash","name":"Ling 3.0 Flash","description":"Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"canonical_model_id":"inclusionai/ling-3.0-flash","display_name":"Ling 3.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"inclusionai/ling-3.1-flash","name":"Ling 3.1 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.9,"cache_read":0.06},"canonical_model_id":"inclusionai/ling-3.1-flash","display_name":"Ling 3.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"inclusionai/ling-3.0-flash-sante","name":"Ling 3.0 Flash Sante","description":"Health and medicine specialization of Ling 3.0 Flash for medical reasoning and evidence-based retrieval","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"canonical_model_id":"inclusionai/ling-3.0-flash-sante","display_name":"Ling 3.0 Flash Sante","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"inclusionai/ling-3.0-flash-vl","name":"Ling 3.0 Flash VL","description":"Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"canonical_model_id":"inclusionai/ling-3.0-flash-vl","display_name":"Ling 3.0 Flash VL","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"inclusionai/ling-3.0-flash-fin","name":"Ling 3.0 Flash Fin","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-08-27","last_updated":"2026-09-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"canonical_model_id":"inclusionai/ling-3.0-flash-fin","display_name":"Ling 3.0 Flash Fin","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.8,"output":3.4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","description":"Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.57,"output":2.3},"canonical_model_id":"moonshotai/kimi-k2-instruct","display_name":"Kimi K2 Instruct","type":"chat"},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 Instruct 0905","description":"September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.6,"output":2.5},"canonical_model_id":"moonshotai/kimi-k2-0905","display_name":"Kimi K2 Instruct 0905","type":"chat"},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.055},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM-4.6V","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM-4.5V","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1.38,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/autoglm-phone-9b-multilingual","name":"AutoGLM Phone 9B Multilingual","description":"Multilingual visual model for operating smartphone interfaces and mobile agents","family":"glm","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-10","last_updated":"2025-12-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.035,"output":0.138},"canonical_model_id":"zhipuai/autoglm-phone-9b-multilingual","display_name":"AutoGLM Phone 9B Multilingual","type":"chat"},{"id":"zai-org/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.13,"output":0.85,"cache_read":0.025},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5-Air","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"apodex/apodex-1.1-mini","name":"Apodex 1.1 Mini","description":"Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted work","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-24","last_updated":"2026-08-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"apodex/apodex-1.1-mini","display_name":"Apodex 1.1 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.2},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax L2 13B","description":"Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2023-08-10","last_updated":"2023-08-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":3200},"cost":{"input":0.09,"output":0.09},"canonical_model_id":"gryphe/mythomax-l2-13b","display_name":"MythoMax L2 13B","type":"chat"},{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":524288}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"paddlepaddle/paddleocr-vl","name":"PaddleOCR VL","description":"Compact vision-language model for multilingual document parsing, OCR, tables, formulas, and charts","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.02,"output":0.02},"canonical_model_id":"paddlepaddle/paddleocr-vl","display_name":"PaddleOCR VL","type":"chat"},{"id":"stepfun/step-5-preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":1,"output":2.7,"cache_read":0.1},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":256000,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mindai/macaron-v1-tall","name":"Macaron V1 Tall","description":"Qwen3.6-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2475,"output":1.43,"cache_read":0.044},"canonical_model_id":"mindlab/macaron-v1-tall","display_name":"Macaron V1 Tall","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mindai/macaron-v1-venti","name":"Macaron V1 Venti","description":"GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.825,"output":2.475,"cache_read":0.165},"canonical_model_id":"mindlab/macaron-v1-venti","display_name":"Macaron V1 Venti","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.42,"output":3,"cache_read":0.085},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3-omni-30b-a3b-thinking","name":"Qwen3 Omni 30B A3B Thinking","description":"Multimodal reasoning model accepting text, images, video, and audio with text output","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.25,"output":0.97,"input_audio":2.2},"canonical_model_id":"alibaba/qwen3-omni-30b-a3b-thinking","display_name":"Qwen3 Omni 30B A3B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-reranker-8b","type":"rerank","name":"Qwen3 Reranker 8B","description":"Multilingual query-document reranking model supporting more than 100 languages","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.05,"output":0},"canonical_model_id":"alibaba/qwen3-reranker-8b","display_name":"Qwen3 Reranker 8B"},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-10-04","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.7},"canonical_model_id":"alibaba/qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","type":"chat"},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-mt-plus","name":"Qwen MT Plus","description":"Flagship Qwen translation model with terminology control and support for 92 languages","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-07-24","last_updated":"2025-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":0.25,"output":0.75},"canonical_model_id":"alibaba/qwen-mt-plus","display_name":"Qwen MT Plus","type":"chat"},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3-embedding-8b","type":"embedding","name":"Qwen3 Embedding 8B","description":"Multilingual text embedding model for retrieval, code search, classification, and clustering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.07,"output":0},"canonical_model_id":"alibaba/qwen3-embedding-8b","display_name":"Qwen3 Embedding 8B"},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"baichuan/baichuan-m2-32b","name":"Baichuan M2 32B","description":"Open medical model trained for clinical reasoning and patient interaction with on, off, and auto thinking modes","family":"baichuan","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.07,"output":0.07},"canonical_model_id":"baichuan/baichuan-m2-32b","display_name":"Baichuan M2 32B","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.25},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM 2 8x22B","description":"Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-04-15","last_updated":"2024-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65535,"output":8000},"cost":{"input":0.62,"output":0.62},"canonical_model_id":"microsoft/wizardlm-2-8x22b","display_name":"WizardLM 2 8x22B","type":"chat"}]},"302ai":{"id":"302ai","api":"https://api.302.ai/v1","name":"302.AI","doc":"https://doc.302.ai","display_name":"302.AI","models":[{"id":"grok-4-1-fast-reasoning","name":"grok-4-1-fast-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"display_name":"grok-4-1-fast-reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.145,"output":0.43},"display_name":"GLM-4.6V","type":"chat"},{"id":"gpt-5.4","name":"gpt-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"tiers":[{"input":5,"output":22.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5}},"display_name":"gpt-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.286,"output":1.142},"display_name":"GLM-4.5","type":"chat"},{"id":"claude-haiku-4-5","name":"claude-haiku-4-5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5},"display_name":"claude-haiku-4-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.8,"output":5.3},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-image-preview","name":"gemini-3.1-flash-image-preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":true},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-27","last_updated":"2026-02-27","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":60},"display_name":"gemini-3.1-flash-image-preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.72,"output":2.88},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4-nano","name":"gpt-5.4-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25},"display_name":"gpt-5.4-nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3.5-flash-thinking","name":"gemini-3.5-flash-thinking","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9},"canonical_model_id":"google/gemini-3.5-flash","display_name":"gemini-3.5-flash-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3-pro-preview","name":"gemini-3-pro-preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12},"display_name":"gemini-3-pro-preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5v-turbo","name":"GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0.72,"output":3.2},"display_name":"GLM-5V-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.5-flash-image","name":"gemini-2.5-flash-image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-08","last_updated":"2025-10-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30},"display_name":"gemini-2.5-flash-image","type":"image-generation"},{"id":"gpt-4o","name":"gpt-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"display_name":"gpt-4o","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.075,"output":0.25},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.6","name":"glm-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.286,"output":1.142},"display_name":"glm-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3-235b-a22b-instruct-2507","name":"qwen3-235b-a22b-instruct-2507","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":65536},"cost":{"input":0.29,"output":1.143},"display_name":"qwen3-235b-a22b-instruct-2507","type":"chat"},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.16,"output":6.36},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.6-sol-pro","name":"gpt-5.6-sol-pro","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"gpt-5.6-sol-pro","type":"chat"},{"id":"gpt-5-mini","name":"gpt-5-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2},"display_name":"gpt-5-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.12,"output":0.69},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-sonnet-4-6-thinking","name":"claude-sonnet-4-6-thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2026-02-18","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"display_name":"claude-sonnet-4-6-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"glm-5","name":"glm-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.6},"display_name":"glm-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-4.1-nano","name":"gpt-4.1-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4},"display_name":"gpt-4.1-nano","type":"chat"},{"id":"grok-4-fast-reasoning","name":"grok-4-fast-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"display_name":"grok-4-fast-reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.2-chat-latest","name":"gpt-5.2-chat-latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-12","last_updated":"2025-12-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14},"display_name":"gpt-5.2-chat-latest","type":"chat"},{"id":"gpt-5.1-chat-latest","name":"gpt-5.1-chat-latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10},"display_name":"gpt-5.1-chat-latest","type":"chat"},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"MiniMax-M2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-flash-preview-09-2025","name":"gemini-2.5-flash-preview-09-2025","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":2.5},"display_name":"gemini-2.5-flash-preview-09-2025","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16384},"cost":{"input":0.29,"output":0.86},"display_name":"GLM-4.5V","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-opus-5-thinking","name":"claude-opus-5-thinking","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"claude-opus-5-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true}}},{"id":"qwen3-coder-480b-a35b-instruct","name":"qwen3-coder-480b-a35b-instruct","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.86,"output":3.43},"display_name":"qwen3-coder-480b-a35b-instruct","type":"chat"},{"id":"doubao-seed-1-6-vision-250815","name":"doubao-seed-1-6-vision-250815","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.114,"output":1.143},"display_name":"doubao-seed-1-6-vision-250815","type":"chat"},{"id":"claude-sonnet-4-5-20250929-thinking","name":"claude-sonnet-4-5-20250929-thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"display_name":"claude-sonnet-4-5-20250929-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2-thinking","name":"kimi-k2-thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.575,"output":2.3},"display_name":"kimi-k2-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-4-fast-non-reasoning","name":"grok-4-fast-non-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"display_name":"grok-4-fast-non-reasoning","type":"chat"},{"id":"grok-4.20-beta-0309-reasoning","name":"grok-4.20-beta-0309-reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6},"display_name":"grok-4.20-beta-0309-reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-1-20250805","name":"claude-opus-4-1-20250805","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"display_name":"claude-opus-4-1-20250805","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5-pro","name":"gpt-5-pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-08","last_updated":"2025-10-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"display_name":"gpt-5-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"claude-opus-4-5-20251101","name":"claude-opus-4-5-20251101","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25},"display_name":"claude-opus-4-5-20251101","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"gemini-3-pro-image-preview","name":"gemini-3-pro-image-preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":64000},"cost":{"input":2,"output":120},"display_name":"gemini-3-pro-image-preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.0-flash-lite","name":"gemini-2.0-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-11","release_date":"2025-06-16","last_updated":"2025-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":8192},"cost":{"input":0.075,"output":0.3},"display_name":"gemini-2.0-flash-lite","type":"chat"},{"id":"qwen3-235b-a22b","name":"Qwen3-235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.29,"output":2.86},"display_name":"Qwen3-235B-A22B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-luna-pro","name":"gpt-5.6-luna-pro","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"gpt-5.6-luna-pro","type":"chat"},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.66,"output":3.3},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.1","name":"gpt-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10},"display_name":"gpt-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.7-max-2026-06-08","name":"qwen3.7-max-2026-06-08","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.8,"output":5.3},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"qwen3.7-max-2026-06-08","type":"chat"},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.283,"output":1.705},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2-0905-preview","name":"kimi-k2-0905-preview","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.632,"output":2.53},"display_name":"kimi-k2-0905-preview","type":"chat"},{"id":"deepseek-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro","name":"gemini-2.5-pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":10},"display_name":"gemini-2.5-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.188,"output":1.133},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.5-flash","name":"gemini-2.5-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":2.5},"display_name":"gemini-2.5-flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"doubao-seed-1-6-thinking-250715","name":"doubao-seed-1-6-thinking-250715","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16000},"cost":{"input":0.121,"output":1.21},"display_name":"doubao-seed-1-6-thinking-250715","type":"chat"},{"id":"gpt-5-thinking","name":"gpt-5-thinking","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10},"display_name":"gpt-5-thinking","type":"chat"},{"id":"MiniMax-M1","name":"MiniMax-M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-06-16","last_updated":"2025-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.132,"output":1.254},"display_name":"MiniMax-M1","type":"chat"},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4-mini","name":"gpt-5.4-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5},"display_name":"gpt-5.4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-4.7","name":"glm-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.286,"output":1.142},"display_name":"glm-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.18,"output":0.564},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.2","name":"gpt-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-12","last_updated":"2025-12-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14},"display_name":"gpt-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2-thinking","name":"DeepSeek-V3.2-Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.29,"output":0.43},"display_name":"DeepSeek-V3.2-Thinking","type":"chat"},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-4-5-20250929","name":"claude-sonnet-4-5-20250929","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"display_name":"claude-sonnet-4-5-20250929","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-4.1","name":"gpt-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8},"display_name":"gpt-4.1","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.06,"output":0.46},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-30b-a3b","name":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.11,"output":1.08},"display_name":"Qwen3-30B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gemini-2.5-flash-nothink","name":"gemini-2.5-flash-nothink","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-24","last_updated":"2025-06-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":2.5},"display_name":"gemini-2.5-flash-nothink","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"doubao-seed-1-8-251215","name":"doubao-seed-1-8-251215","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":224000,"output":64000},"cost":{"input":0.114,"output":0.286},"display_name":"doubao-seed-1-8-251215","type":"chat"},{"id":"claude-opus-4-1-20250805-thinking","name":"claude-opus-4-1-20250805-thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-05-27","last_updated":"2025-05-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"display_name":"claude-opus-4-1-20250805-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gemini-3-flash-preview","name":"gemini-3-flash-preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3},"display_name":"gemini-3-flash-preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-haiku-4-5-20251001","name":"claude-haiku-4-5-20251001","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5},"display_name":"claude-haiku-4-5-20251001","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"mistral-large-2512","name":"mistral-large-2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":262144},"cost":{"input":1.1,"output":3.3},"display_name":"mistral-large-2512","type":"chat"},{"id":"MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-10-26","last_updated":"2025-10-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.33,"output":1.32},"display_name":"MiniMax-M2","type":"chat"},{"id":"gemini-2.5-flash-lite-preview-09-2025","name":"gemini-2.5-flash-lite-preview-09-2025","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":{"supported":true,"default":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4},"display_name":"gemini-2.5-flash-lite-preview-09-2025","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-4.1-mini","name":"gpt-4.1-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6},"display_name":"gpt-4.1-mini","type":"chat"},{"id":"gpt-5.6-terra-pro","name":"gpt-5.6-terra-pro","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"gpt-5.6-terra-pro","type":"chat"},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"ministral-14b-2512","name":"ministral-14b-2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.33,"output":0.33},"display_name":"ministral-14b-2512","type":"chat"},{"id":"glm-5-turbo","name":"glm-5-turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0.72,"output":3.2},"display_name":"glm-5-turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"grok-4.1","name":"grok-4.1","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":2,"output":10},"display_name":"grok-4.1","type":"chat"},{"id":"claude-sonnet-4-6","name":"claude-sonnet-4-6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-18","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"display_name":"claude-sonnet-4-6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14},"canonical_model_id":"openai/gpt-5.3-chat-latest","display_name":"GPT-5.3 Chat (latest)","type":"chat"},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.8},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2","name":"deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.29,"output":0.43},"display_name":"deepseek-v3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7-thinking","name":"claude-opus-4-7-thinking","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"claude-opus-4-7-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-opus-4-7","name":"claude-opus-4-7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"display_name":"claude-opus-4-7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5","name":"gpt-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10},"display_name":"gpt-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"qwen3-max-2025-09-23","name":"qwen3-max-2025-09-23","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":258048,"output":65536},"cost":{"input":0.86,"output":3.43},"display_name":"qwen3-max-2025-09-23","type":"chat"},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.285,"output":1.15},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":10,"cache_read":0.2,"cache_write":0.375},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"perplexity":{"id":"perplexity","name":"Perplexity","doc":"https://docs.perplexity.ai","display_name":"Perplexity","models":[{"id":"sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"display_name":"Sonar Pro","type":"chat"},{"id":"sonar-deep-research","name":"Perplexity Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"display_name":"Perplexity Sonar Deep Research","type":"chat"},{"id":"sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":1,"output":1},"display_name":"Sonar","type":"chat"},{"id":"sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"display_name":"Sonar Reasoning Pro","type":"chat"}]},"iteracompute":{"id":"iteracompute","api":"https://api.iteracompute.com/v1","name":"IteraCompute","doc":"https://iteracompute.com/docs.html","display_name":"IteraCompute","models":[{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 (legacy alias)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.29,"output":1.16,"cache_read":0.0058},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4 Flash 0731 (legacy alias)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.29,"output":1.16,"cache_read":0.0058},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.89,"output":2.69,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.099,"output":0.35,"cache_read":0.025},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.99,"output":3.45,"cache_read":0.245},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":999999},"cost":{"input":2.39,"output":11.99,"cache_read":0.24},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.69,"output":3.29,"cache_read":0.15},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":524288},"cost":{"input":0.299,"output":1.19,"cache_read":0.045},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.95,"output":5.7,"cache_read":0.245},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"the-grid-ai":{"id":"the-grid-ai","api":"https://api.thegrid.ai/v1","name":"The Grid AI","doc":"https://thegrid.ai/docs","display_name":"The Grid AI","models":[{"id":"bytedance-pro-latest","name":"ByteDance Pro Latest","description":"Lab latest market for ByteDance Pro supply. You contract for the latest qualifying route, not a specific model.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":256000,"output":131072},"display_name":"ByteDance Pro Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-latest","name":"MiniMax Latest","description":"Lab latest market for MiniMax supply. You contract for the latest qualifying route, not a specific model.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":512000},"display_name":"MiniMax Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"agent-prime","name":"Agent Prime","description":"Reliable models for dependable agentic applications, multi-step tool use, and reasoning workflows. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"input":120000,"output":131072},"status":"beta","display_name":"Agent Prime","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-latest","name":"Claude Opus Latest","description":"Lab latest market for Claude Opus frontier supply. You contract for the latest qualifying route, not a specific model.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-06","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"display_name":"Claude Opus Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"code-max","name":"Code Max","description":"Frontier models for complex research, architectural decisions, debugging, and multi-file development. Any model that meets the contract spec can serve your request.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-05-04","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"status":"beta","display_name":"Code Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"agent-max","name":"Agent Max","description":"Frontier models for autonomous research, deep multi-step tool chains, and complex long-horizon tasks. Any model that meets the contract spec can serve your request.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-05-04","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"status":"beta","display_name":"Agent Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"text-max","name":"Text Max","description":"Frontier models for deep reasoning, long context, and complex workflows. Any model that meets the contract spec can serve your request.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-02-26","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"display_name":"Text Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-sol-latest","name":"GPT Sol Latest","description":"Lab latest market for GPT frontier supply. You contract for the latest qualifying route, not a specific model.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"display_name":"GPT Sol Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"code-prime","name":"Code Prime","description":"Reliable models for everyday software tasks, code completion, review, and standard debugging. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"input":120000,"output":131072},"status":"beta","display_name":"Code Prime","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"text-prime","name":"Text Prime","description":"Reliable models for everyday text generation, editing, and analysis across diverse workflows. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-26","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"input":120000,"output":131072},"display_name":"Text Prime","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-pro-latest","name":"Gemini Pro Latest","description":"Lab latest market for Gemini Pro frontier supply. You contract for the latest qualifying route, not a specific model.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":65536},"display_name":"Gemini Pro Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-pro-latest","name":"DeepSeek Pro Latest","description":"Lab latest market for DeepSeek Pro supply. You contract for the latest qualifying route, not a specific model.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":384000},"display_name":"DeepSeek Pro Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"code-standard","name":"Code Standard","description":"Price-optimized models for rapid autocomplete, linting, high-frequency suggestions, and batch edits. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":120000,"output":65536},"status":"beta","display_name":"Code Standard","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"text-standard","name":"Text Standard","description":"Price-optimized models with low-latency, high-throughput and shorter maximum outputs. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-26","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":120000,"output":65536},"display_name":"Text Standard","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"agent-standard","name":"Agent Standard","description":"Price-optimized models for fast tool calls, simple agent loops, high-throughput automation, and orchestration. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":120000,"output":65536},"status":"beta","display_name":"Agent Standard","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-latest","name":"GLM Latest","description":"Lab latest market for GLM supply. You contract for the latest qualifying route, not a specific model.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"display_name":"GLM Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"meta":{"id":"meta","api":"https://api.meta.ai/v1","name":"Meta","doc":"https://dev.meta.ai/docs","display_name":"Meta","models":[{"id":"muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2 Contributor","type":"chat"},{"id":"muse-wonder-1.0","name":"Muse Wonder","description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"meta/muse-wonder-1.0","display_name":"Muse Wonder","type":"chat"},{"id":"muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3 Contributor","type":"chat"}]},"cline-pass":{"id":"cline-pass","api":"https://api.cline.bot/api/v1","name":"ClinePass","doc":"https://docs.cline.bot/getting-started/clinepass","display_name":"ClinePass","models":[{"id":"cline-pass/mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"cline-pass/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"cline-pass/glm-5.3-flash","name":"cline-pass/glm-5.3-flash","description":"Latest natively multimodal model in the GLM-5 series","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"display_name":"cline-pass/glm-5.3-flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"cline-pass/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.74,"output":3.48,"cache_read":0.0145},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat"},{"id":"cline-pass/mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"cline-pass/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.0145},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"cline-pass/muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3 Contributor","type":"chat"},{"id":"cline-pass/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"cline-pass/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cline-pass/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"modal":{"id":"modal","api":"https://inference.us-west.modal.direct/v1","name":"Modal","doc":"https://modal.com/docs/guide/endpoints","display_name":"Modal","models":[{"id":"thinkingmachines/Inkling-NVFP4","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.2,"output":5,"cache_read":0.27},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8-Max","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1010000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8-Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"reasoning":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.45,"output":1.5,"cache_read":0.09},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"coralbricks":{"id":"coralbricks","api":"https://inference.coralbricks.ai/v1","name":"CoralBricks","doc":"https://www.coralbricks.ai/docs","display_name":"CoralBricks","models":[{"id":"glm-5.3-fp4","name":"GLM 5.3 FP4","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.12,"output":4.4,"cache_read":0,"cache_write":1.68},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 FP4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4.1-flash-fast","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.01,"output":1.2,"cache_read":0,"cache_write":0.09},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.3-fast","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.12,"output":4.4,"cache_read":0,"cache_write":1.68},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4.1-flash-fast-fp4","name":"DeepSeek V4.1 Flash FP4","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.01,"output":1.2,"cache_read":0,"cache_write":0.09},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash FP4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}}]},"routing-run":{"id":"routing-run","api":"https://api.routing.run/v1","name":"routing.run","doc":"https://docs.routing.run/api-reference/models","display_name":"routing.run","models":[{"id":"nemotron-3-ultra","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32000},"cost":{"input":0.1,"output":0.1},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32000},"cost":{"input":0.16,"output":0.48},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":0.7,"output":4.2},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"glm-5.2-nitro","name":"GLM 5.2 Nitro","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.8,"output":2.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Nitro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.8,"output":2.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.6-nitro","name":"Kimi K2.6 Nitro","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 Nitro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.348,"output":0.696},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"kimi-k2.7-code-nitro","name":"Kimi K2.7 Code Nitro","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code Nitro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":1.5,"output":9},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.112,"output":0.224},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"echo":{"id":"echo","api":"https://echo.tracerml.ai/v1","name":"Echo","doc":"https://echo.tracerml.ai/docs/api","display_name":"Echo","models":[{"id":"echo","name":"Echo","description":"Adaptive model for coding, reasoning, and tool-driven agent workflows through one OpenAI-compatible endpoint","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"status":"beta","cost":{"input":10,"output":50},"display_name":"Echo","type":"chat"}]},"neuralwatt":{"id":"neuralwatt","api":"https://api.neuralwatt.com/v1","name":"Neuralwatt","doc":"https://portal.neuralwatt.com/docs","display_name":"Neuralwatt","models":[{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"cost":{"input":0.87,"output":1.74,"cache_read":0.036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.2-short-fast","name":"GLM 5.2 Short Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":32000},"status":"deprecated","cost":{"input":1.45,"output":4.5,"cache_read":0.145},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Short Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"kimi-k3-flex","name":"Kimi K3 Flex","description":"Kimi K3 on the flex tier: discounted, best-effort latency, requests may be held under load","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":1.95,"output":9.75,"cache_read":0.195},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4-flash-flex","name":"DeepSeek V4 Flash Flex","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"cost":{"input":0.091,"output":0.182,"cache_read":0.0182},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.2-short-flex","name":"GLM 5.2 Short Flex","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":32000},"status":"deprecated","cost":{"input":0.9425,"output":2.925,"cache_read":0.09425},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Short Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"qwen3.6-35b","name":"Qwen3.6 35B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131056,"output":131056},"cost":{"input":0.29,"output":1.15,"cache_read":0.029},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2-fast","name":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"status":"deprecated","cost":{"input":1.45,"output":4.5,"cache_read":0.145},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"kimi-k3-fast","name":"Kimi K3 Fast","description":"Kimi K3 with thinking disabled for low-latency tool calling, vision, and JSON work","family":"kimi-k3","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 Fast","type":"chat"},{"id":"qwen3.6-35b-flex","name":"Qwen3.6 35B Flex","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131056,"output":131056},"cost":{"input":0.1885,"output":0.7475,"cache_read":0.01885},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":131072},"cost":{"input":0.45,"output":3.2,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.2-short","name":"GLM 5.2 Short","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":32000},"status":"deprecated","cost":{"input":1.45,"output":4.5,"cache_read":0.145},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Short","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.3-flash-flex","name":"GLM-5.3 Flash Flex","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":0.0975,"output":0.325,"cache_read":0.0195},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"qwen3.6-35b-fast","name":"Qwen3.6 35B Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen3.6","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131056,"output":131056},"cost":{"input":0.29,"output":1.15,"cache_read":0.029},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2-flex","name":"GLM 5.2 Flex","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"status":"deprecated","cost":{"input":0.9425,"output":2.925,"cache_read":0.09425},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4-flash-speed","name":"DeepSeek V4 Flash (Speed)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash (Speed)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"mimo-v2.6-pro-flex","name":"MiMo-V2.6-Pro Flex","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"cost":{"input":0.5655,"output":1.131,"cache_read":0.0234},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.2","name":"GLM 5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"status":"deprecated","cost":{"input":1.45,"output":4.5,"cache_read":0.145},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.2-short-fast-flex","name":"GLM 5.2 Short Fast Flex","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":32000},"status":"deprecated","cost":{"input":0.9425,"output":2.925,"cache_read":0.09425},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Short Fast Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"kimi-k2.7-code-fast","name":"Kimi K2.7 Code Fast","description":"Kimi K2.7 Code with reasoning capped to a short budget for lower latency; reasoning cannot be disabled on this model","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.95,"output":4,"cache_read":0.095},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"gemma-4-31b","name":"Gemma 4 31B","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":16384},"cost":{"input":0.144,"output":0.42,"cache_read":0.0144},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.3-flex","name":"GLM 5.3 Flex","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":0.9425,"output":2.925,"cache_read":0.09425},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"status":"deprecated","cost":{"input":1,"output":3,"cache_read":0.1},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"qwen-3.8-27b-flex","name":"Qwen3.8 27B Flex","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":131072},"cost":{"input":0.2925,"output":2.08,"cache_read":0.1625},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"kimi-k2.7-code-flex","name":"Kimi K2.7 Code Flex","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.6175,"output":2.6,"cache_read":0.06175},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":1.45,"output":4.5,"cache_read":0.145},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.95,"output":4,"cache_read":0.095},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4.1-flash-flex","name":"DeepSeek V4.1 Flash Flex","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"cost":{"input":0.0975,"output":0.39,"cache_read":0.00975},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash Flex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"gitlab":{"id":"gitlab","name":"GitLab Duo","doc":"https://docs.gitlab.com/user/duo_agent_platform/","display_name":"GitLab Duo","models":[{"id":"duo-chat-gpt-5-4-nano","name":"Agentic Chat (GPT-5.4 Nano)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.4 Nano)","type":"chat"},{"id":"duo-chat-opus-5-5","name":"Agentic Chat (Claude Opus 5.5)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Agentic Chat (Claude Opus 5.5)","type":"chat"},{"id":"duo-chat-gpt-6-1-sol","name":"Agentic Chat (GPT-6.1 Sol)","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"Agentic Chat (GPT-6.1 Sol)","type":"chat"},{"id":"duo-chat-sonnet-5-5","name":"Agentic Chat (Claude Sonnet 5.5)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Agentic Chat (Claude Sonnet 5.5)","type":"chat"},{"id":"duo-chat-gpt-6-astra","name":"Agentic Chat (GPT-6 Astra)","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-6-astra","display_name":"Agentic Chat (GPT-6 Astra)","type":"chat"},{"id":"duo-chat-opus-4-5","name":"Agentic Chat (Claude Opus 4.5)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2026-01-08","last_updated":"2026-01-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Agentic Chat (Claude Opus 4.5)","type":"chat"},{"id":"duo-chat-gpt-5-mini","name":"Agentic Chat (GPT-5 Mini)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5 Mini)","type":"chat"},{"id":"duo-chat-gpt-6-luna","name":"Agentic Chat (GPT-6 Luna)","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-6-luna","display_name":"Agentic Chat (GPT-6 Luna)","type":"chat"},{"id":"duo-chat-sonnet-4-5","name":"Agentic Chat (Claude Sonnet 4.5)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2026-01-08","last_updated":"2026-01-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Agentic Chat (Claude Sonnet 4.5)","type":"chat"},{"id":"duo-chat-gpt-5-6-sol","name":"Agentic Chat (GPT-5.6 Sol)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"Agentic Chat (GPT-5.6 Sol)","type":"chat"},{"id":"duo-chat-sonnet-4-6","name":"Agentic Chat (Claude Sonnet 4.6)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Agentic Chat (Claude Sonnet 4.6)","type":"chat"},{"id":"duo-chat-gpt-5-4-mini","name":"Agentic Chat (GPT-5.4 Mini)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.4 Mini)","type":"chat"},{"id":"duo-chat-haiku-4-5","name":"Agentic Chat (Claude Haiku 4.5)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2026-01-08","last_updated":"2026-01-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Agentic Chat (Claude Haiku 4.5)","type":"chat"},{"id":"duo-chat-fable-5-1","name":"Agentic Chat (Claude Fable 5.1)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Agentic Chat (Claude Fable 5.1)","type":"chat"},{"id":"duo-chat-gpt-5-5","name":"Agentic Chat (GPT-5.5)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.5)","type":"chat"},{"id":"duo-chat-fable-5","name":"Agentic Chat (Claude Fable 5)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Agentic Chat (Claude Fable 5)","type":"chat"},{"id":"duo-chat-gpt-5-3-codex","name":"Agentic Chat (GPT-5.3 Codex)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.3 Codex)","type":"chat"},{"id":"duo-chat-gpt-5-1","name":"Agentic Chat (GPT-5.1)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.1)","type":"chat"},{"id":"duo-chat-gpt-6-sol","name":"Agentic Chat (GPT-6 Sol)","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-6-sol","display_name":"Agentic Chat (GPT-6 Sol)","type":"chat"},{"id":"duo-chat-opus-4-7","name":"Agentic Chat (Claude Opus 4.7)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Agentic Chat (Claude Opus 4.7)","type":"chat"},{"id":"duo-chat-gpt-5-2","name":"Agentic Chat (GPT-5.2)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.2)","type":"chat"},{"id":"duo-chat-opus-5","name":"Agentic Chat (Claude Opus 5)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Agentic Chat (Claude Opus 5)","type":"chat"},{"id":"duo-chat-opus-4-6","name":"Agentic Chat (Claude Opus 4.6)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Agentic Chat (Claude Opus 4.6)","type":"chat"},{"id":"duo-chat-gpt-5-6-luna","name":"Agentic Chat (GPT-5.6 Luna)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"Agentic Chat (GPT-5.6 Luna)","type":"chat"},{"id":"duo-chat-gpt-5-codex","name":"Agentic Chat (GPT-5 Codex)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5 Codex)","type":"chat"},{"id":"duo-chat-sonnet-5","name":"Agentic Chat (Claude Sonnet 5)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Agentic Chat (Claude Sonnet 5)","type":"chat"},{"id":"duo-chat-opus-4-8","name":"Agentic Chat (Claude Opus 4.8)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Agentic Chat (Claude Opus 4.8)","type":"chat"},{"id":"duo-chat-gpt-5-2-codex","name":"Agentic Chat (GPT-5.2 Codex)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.2 Codex)","type":"chat"},{"id":"duo-chat-gpt-5-4","name":"Agentic Chat (GPT-5.4)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"display_name":"Agentic Chat (GPT-5.4)","type":"chat"},{"id":"duo-chat-gpt-5-6-terra","name":"Agentic Chat (GPT-5.6 Terra)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"Agentic Chat (GPT-5.6 Terra)","type":"chat"}]},"infer":{"id":"infer","api":"https://infer.flow7.org/v1","name":"Infer by Flow7","doc":"https://infer.flow7.org/opencode","display_name":"Infer by Flow7","models":[{"id":"infer/gpt-6-astra:official","name":"GPT-6 Astra (Official API)","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":271999,"output":128000},"provider":{"shape":"responses"},"cost":{"input":12.5,"output":62.5,"cache_read":1.25,"cache_write":15.625},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra (Official API)","type":"chat"},{"id":"infer/gpt-5.6-sol:official","name":"GPT-5.6 Sol (Official API)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":271999,"output":128000},"provider":{"shape":"responses"},"cost":{"input":2.5,"output":12.5,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol (Official API)","type":"chat"}]},"azure":{"id":"azure","name":"Azure","doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","display_name":"Azure","models":[{"id":"grok-4-1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast (Reasoning)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2-speciale","name":"DeepSeek-V3.2-Speciale","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"display_name":"DeepSeek-V3.2-Speciale","type":"chat"},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast (Non-Reasoning)","type":"chat"},{"id":"phi-4-reasoning","name":"Phi-4-reasoning","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"display_name":"Phi-4-reasoning","type":"chat"},{"id":"grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"status":"beta","canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.02,"output":0},"display_name":"text-embedding-3-small","type":"embedding"},{"id":"gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"ministral-3b","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.04,"output":0.04},"display_name":"Ministral 3B","type":"chat"},{"id":"gpt-chat-latest","name":"GPT Chat Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-05-05","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"status":"beta","cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5-instant","display_name":"GPT Chat Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"display_name":"GPT-5-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-image-2","name":"GPT-Image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2","display_name":"GPT-Image-2","type":"image-generation"},{"id":"o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B 128E Instruct FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0.25,"output":1},"display_name":"Llama 4 Maverick 17B 128E Instruct FP8","type":"chat"},{"id":"o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.1,"output":0},"display_name":"text-embedding-ada-002","type":"embedding"},{"id":"deepseek-v4.1-flash","name":"DeepSeek-V4.1-Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek-V4.1-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"phi-4-multimodal","name":"Phi-4-multimodal","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"phi","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.08,"output":0.32,"input_audio":4},"display_name":"Phi-4-multimodal","type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.95,"output":4},"display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"gpt-image-2.5-flare","name":"GPT Image 2.5 Flare","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2.5-flare","display_name":"GPT Image 2.5 Flare","type":"image-generation"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.4,"output":2},"display_name":"Mistral Medium 3","type":"chat"},{"id":"cohere-embed-v3-multilingual","name":"Embed v3 Multilingual","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"display_name":"Embed v3 Multilingual","type":"chat"},{"id":"o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"codex-mini","name":"Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-04","release_date":"2025-05-16","last_updated":"2025-05-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.5,"output":6,"cache_read":0.375},"display_name":"Codex Mini","type":"chat"},{"id":"phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"display_name":"Phi-4-reasoning-plus","type":"chat"},{"id":"claude-mythos-5","name":"Claude Mythos 5","description":"Restricted Claude model for advanced cybersecurity and biology research workflows","family":"claude-mythos","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-mythos-5","display_name":"Claude Mythos 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-3.5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-09-21","last_updated":"2023-09-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":4096},"status":"deprecated","cost":{"input":1.5,"output":2},"display_name":"GPT-3.5 Turbo Instruct","type":"chat"},{"id":"gpt-3.5-turbo-0125","name":"GPT-3.5 Turbo 0125","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":4096},"status":"deprecated","cost":{"input":0.5,"output":1.5},"display_name":"GPT-3.5 Turbo 0125","type":"chat"},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":3072},"cost":{"input":0.13,"output":0},"display_name":"text-embedding-3-large","type":"embedding"},{"id":"claude-opus-4-1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"cohere-embed-v-4-0","name":"Embed v4","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":1536},"cost":{"input":0.12,"output":0},"display_name":"Embed v4","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"codestral-2501","name":"Codestral 25.01","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":0.9},"display_name":"Codestral 25.01","type":"chat"},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.6,"output":3},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.1","name":"GPT-5.1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":2.5,"output":20,"cache_read":0.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.71,"output":0.71},"display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"cohere-command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.5,"output":10},"display_name":"Command A","type":"chat"},{"id":"cohere-embed-v3-english","name":"Embed v3 English","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"display_name":"Embed v3 English","type":"chat"},{"id":"model-router","name":"Model Router","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"model-router","attachment":true,"reasoning":{"supported":false},"tool_call":true,"release_date":"2025-05-19","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"provider":{"shape":"completions"},"cost":{"input":0.14,"output":0},"display_name":"Model Router","type":"chat"},{"id":"gpt-image-2.5-sunburst","name":"GPT Image 2.5 Sunburst","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2.5-sunburst","display_name":"GPT Image 2.5 Sunburst","type":"image-generation"},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-image-1","name":"GPT-Image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":40,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-1","display_name":"GPT-Image-1","type":"image-generation"},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT-5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":28,"cache_read":0.35},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":1.75,"output":14,"cache_read":0.125},"display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-12-31","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"phi-4","name":"Phi-4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.125,"output":0.5},"display_name":"Phi-4","type":"chat"},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mistral-small-2503","name":"Mistral Small 3.1","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":0.1,"output":0.3},"display_name":"Mistral Small 3.1","type":"chat"},{"id":"phi-4-mini-reasoning","name":"Phi-4-mini-reasoning","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"display_name":"Phi-4-mini-reasoning","type":"chat"},{"id":"gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-07-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-4-turbo-vision","name":"GPT-4 Turbo Vision","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"display_name":"GPT-4 Turbo Vision","type":"chat"},{"id":"grok-4-20-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":8192},"status":"beta","cost":{"input":2,"output":6},"display_name":"Grok 4.20 (Non-Reasoning)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-3.5-turbo-1106","name":"GPT-3.5 Turbo 1106","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":4096},"status":"deprecated","cost":{"input":1,"output":2},"display_name":"GPT-3.5 Turbo 1106","type":"chat"},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"status":"deprecated","cost":{"input":1.35,"output":5.4},"display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":1.74,"output":3.48},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek-V4-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.78},"display_name":"Llama 4 Scout 17B 16E Instruct","type":"chat"},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"gpt-image-1.5","name":"GPT-Image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":32,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-1.5","display_name":"GPT-Image-1.5","type":"image-generation"},{"id":"grok-4-20-reasoning","name":"Grok 4.20 (Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":8192},"status":"beta","cost":{"input":2,"output":6},"display_name":"Grok 4.20 (Reasoning)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":4,"output":24,"cache_read":0.4,"cache_write":5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"display_name":"DeepSeek-V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"GPT-5.1 Codex Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"status":"beta","cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":8,"output":40,"cache_read":0.8,"cache_write":10},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":4,"output":20,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"phi-4-mini","name":"Phi-4-mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"display_name":"Phi-4-mini","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.19,"output":0.51},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek-V4-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"freemodel":{"id":"freemodel","api":"https://cc.freemodel.dev/v1","name":"FreeModel","doc":"https://freemodel.dev","display_name":"FreeModel","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":1.75},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}}]},"azure-cognitive-services":{"id":"azure-cognitive-services","name":"Azure Cognitive Services","doc":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","display_name":"Azure Cognitive Services","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-chat-latest","name":"GPT Chat Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-05-05","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"status":"beta","cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5-instant","display_name":"GPT Chat Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.95,"output":4},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-mythos-5","name":"Claude Mythos 5","description":"Restricted Claude model for advanced cybersecurity and biology research workflows","family":"claude-mythos","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-mythos-5","display_name":"Claude Mythos 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"claude-opus-4-1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.6,"output":3},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25,"tiers":[{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-12-31","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-07-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":4,"output":24,"cache_read":0.4,"cache_write":5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":8,"output":40,"cache_read":0.8,"cache_write":10},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"phi-4-mini","name":"Phi-4-mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"display_name":"Phi-4-mini","type":"chat"},{"id":"gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"GPT-5.1 Codex Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"display_name":"DeepSeek-V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-image-1.5","name":"GPT-Image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":32,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-1.5","display_name":"GPT-Image-1.5","type":"image-generation"},{"id":"llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.78},"display_name":"Llama 4 Scout 17B 16E Instruct","type":"chat"},{"id":"deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"status":"deprecated","cost":{"input":1.35,"output":5.4},"display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"gpt-3.5-turbo-1106","name":"GPT-3.5 Turbo 1106","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":4096},"status":"deprecated","cost":{"input":1,"output":2},"display_name":"GPT-3.5 Turbo 1106","type":"chat"},{"id":"gpt-4-turbo-vision","name":"GPT-4 Turbo Vision","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"display_name":"GPT-4 Turbo Vision","type":"chat"},{"id":"gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"phi-4-mini-reasoning","name":"Phi-4-mini-reasoning","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"display_name":"Phi-4-mini-reasoning","type":"chat"},{"id":"mistral-small-2503","name":"Mistral Small 3.1","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":0.1,"output":0.3},"display_name":"Mistral Small 3.1","type":"chat"},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"phi-4","name":"Phi-4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.125,"output":0.5},"display_name":"Phi-4","type":"chat"},{"id":"gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":28,"cache_read":0.35},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":1.75,"output":14,"cache_read":0.125},"display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT-5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-image-1","name":"GPT-Image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":40,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-1","display_name":"GPT-Image-1","type":"image-generation"},{"id":"gpt-image-2.5-sunburst","name":"GPT Image 2.5 Sunburst","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2.5-sunburst","display_name":"GPT Image 2.5 Sunburst","type":"image-generation"},{"id":"model-router","name":"Model Router","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"model-router","attachment":true,"reasoning":{"supported":false},"tool_call":true,"release_date":"2025-05-19","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"provider":{"shape":"completions"},"cost":{"input":0.14,"output":0},"display_name":"Model Router","type":"chat"},{"id":"cohere-embed-v3-english","name":"Embed v3 English","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"display_name":"Embed v3 English","type":"chat"},{"id":"cohere-command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.5,"output":10},"display_name":"Command A","type":"chat"},{"id":"gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.71,"output":0.71},"display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"gpt-5.1","name":"GPT-5.1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":2.5,"output":20,"cache_read":0.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"codestral-2501","name":"Codestral 25.01","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":0.9},"display_name":"Codestral 25.01","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cohere-embed-v-4-0","name":"Embed v4","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":1536},"cost":{"input":0.12,"output":0},"display_name":"Embed v4","type":"chat"},{"id":"text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":3072},"cost":{"input":0.13,"output":0},"display_name":"text-embedding-3-large","type":"embedding"},{"id":"gpt-3.5-turbo-0125","name":"GPT-3.5 Turbo 0125","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":4096},"status":"deprecated","cost":{"input":0.5,"output":1.5},"display_name":"GPT-3.5 Turbo 0125","type":"chat"},{"id":"gpt-3.5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-09-21","last_updated":"2023-09-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":4096},"status":"deprecated","cost":{"input":1.5,"output":2},"display_name":"GPT-3.5 Turbo Instruct","type":"chat"},{"id":"gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"display_name":"Phi-4-reasoning-plus","type":"chat"},{"id":"codex-mini","name":"Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-04","release_date":"2025-05-16","last_updated":"2025-05-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.5,"output":6,"cache_read":0.375},"display_name":"Codex Mini","type":"chat"},{"id":"o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"cohere-embed-v3-multilingual","name":"Embed v3 Multilingual","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"display_name":"Embed v3 Multilingual","type":"chat"},{"id":"mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.4,"output":2},"display_name":"Mistral Medium 3","type":"chat"},{"id":"gpt-image-2.5-flare","name":"GPT Image 2.5 Flare","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2.5-flare","display_name":"GPT Image 2.5 Flare","type":"image-generation"},{"id":"phi-4-multimodal","name":"Phi-4-multimodal","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"phi","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.08,"output":0.32,"input_audio":4},"display_name":"Phi-4-multimodal","type":"chat"},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.1,"output":0},"display_name":"text-embedding-ada-002","type":"embedding"},{"id":"o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B 128E Instruct FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0.25,"output":1},"display_name":"Llama 4 Maverick 17B 128E Instruct FP8","type":"chat"},{"id":"o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-image-2","name":"GPT-Image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2","display_name":"GPT-Image-2","type":"image-generation"},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"display_name":"GPT-5-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"ministral-3b","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.04,"output":0.04},"display_name":"Ministral 3B","type":"chat"},{"id":"gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.02,"output":0},"display_name":"text-embedding-3-small","type":"embedding"},{"id":"phi-4-reasoning","name":"Phi-4-reasoning","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"display_name":"Phi-4-reasoning","type":"chat"},{"id":"deepseek-v3.2-speciale","name":"DeepSeek-V3.2-Speciale","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"display_name":"DeepSeek-V3.2-Speciale","type":"chat"}]},"pendra":{"id":"pendra","api":"https://api.pendra.ai/api/v1","name":"Pendra","doc":"https://pendra.ai/docs/integrations/opencode","display_name":"Pendra","models":[{"id":"llama3.3:70b","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"qwen3-coder:30b","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"gpt-oss:120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat"},{"id":"qwen3.6:27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat"},{"id":"glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"moark":{"id":"moark","api":"https://moark.com/v1","name":"Moark","doc":"https://moark.com/docs/openapi/v1#tag/%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90","display_name":"Moark","models":[{"id":"Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.98,"output":4},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.3},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.42,"output":2.2},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.29,"output":1.2},"display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.5,"output":0.5},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.8,"output":3.6},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.29,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen3.6-Flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.18,"output":1.03},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.2,"output":4.18},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"atomic-chat":{"id":"atomic-chat","api":"http://127.0.0.1:1337/v1","name":"Atomic Chat","doc":"https://atomic.chat","display_name":"Atomic Chat","models":[{"id":"gemma-4-E4B-it-MLX-4bit","name":"Gemma 4 E4B Instruct (MLX 4-bit)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Gemma 4 E4B Instruct (MLX 4-bit)","type":"chat"},{"id":"Meta-Llama-3_1-8B-Instruct-GGUF","name":"Meta Llama 3.1 8B Instruct (GGUF)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0,"output":0},"display_name":"Meta Llama 3.1 8B Instruct (GGUF)","type":"chat"},{"id":"Qwen3_5-9B-Q4_K_M","name":"Qwen 3.5 9B (Q4_K_M)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-03-05","last_updated":"2026-04-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen 3.5 9B (Q4_K_M)","type":"chat"},{"id":"gemma-4-E4B-it-IQ4_XS","name":"Gemma 4 E4B Instruct (IQ4_XS)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Gemma 4 E4B Instruct (IQ4_XS)","type":"chat"},{"id":"Qwen3_5-9B-MLX-4bit","name":"Qwen 3.5 9B (MLX 4-bit)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-03-05","last_updated":"2026-04-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen 3.5 9B (MLX 4-bit)","type":"chat"}]},"qihang-ai":{"id":"qihang-ai","api":"https://api.qhaigc.net/v1","name":"QiHang","doc":"https://www.qhaigc.net/docs","display_name":"QiHang","models":[{"id":"gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.14,"output":1.14},"display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3-pro-preview","name":"Gemini 3 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.57,"output":3.43},"display_name":"Gemini 3 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5-mini","name":"GPT-5-Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.04,"output":0.29},"display_name":"GPT-5-Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":0.71,"output":3.57},"display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.09,"output":0.71,"tiers":[{"input":0.09,"output":0.71,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.09,"output":0.71}},"display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2},"display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.43,"output":2.14},"display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.07,"output":0.43,"tiers":[{"input":0.07,"output":0.43,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.07,"output":0.43}},"display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.14,"output":0.71},"display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}}]},"ai-router":{"id":"ai-router","api":"https://api.ai-router.dev/v1","name":"AI-ROUTER","doc":"https://ai-router.dev/openai-compatible-api-gateway/","display_name":"AI-ROUTER","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"llmtr":{"id":"llmtr","api":"https://llmtr.com/v1","name":"LLMTR","doc":"https://llmtr.com/docs","display_name":"LLMTR","models":[{"id":"muse-glimmer-30b-tr","name":"Muse Glimmer 30B (TR)","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":2,"output":5,"cache_read":0.5},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B (TR)","type":"chat"},{"id":"magibu-11b-v8","name":"Magibu 11B v8","description":"Turkish-language chat model for instruction following and assistant flows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-06-05","last_updated":"2026-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.1,"output":0.5},"display_name":"Magibu 11B v8","type":"chat"},{"id":"gemma-4","name":"Gemma 4","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":2,"output":5,"cache_read":0.5},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4","type":"chat"},{"id":"trendyol-asure-12b","name":"Trendyol Asure 12B","description":"Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-19","last_updated":"2026-02-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0.1,"output":0.5,"cache_read":0.025},"canonical_model_id":"trendyol/asure-12b","display_name":"Trendyol Asure 12B","type":"chat"},{"id":"medgemma-4b","name":"MedGemma 4B","description":"Multimodal medical-domain Gemma variant for text and image analysis","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-26","last_updated":"2026-08-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"status":"deprecated","cost":{"input":3,"output":5},"display_name":"MedGemma 4B","type":"chat"},{"id":"qwen3-6-35b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":5,"output":10},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat"},{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"poolside/laguna-xs-2.1","display_name":"Laguna XS 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"publicai/apertus-70b-instruct","name":"Apertus 70B Instruct","description":"Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":8192},"cost":{"input":0.82,"output":2.92},"canonical_model_id":"swiss-ai/apertus-70b","display_name":"Apertus 70B Instruct","type":"chat"},{"id":"publicai/apertus-8b-instruct","name":"Apertus 8B Instruct","description":"Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":8192},"cost":{"input":0.1,"output":0.2},"canonical_model_id":"swiss-ai/apertus-8b","display_name":"Apertus 8B Instruct","type":"chat"},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.58,"output":1.44},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat"},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.87,"output":4.68},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"perplexity/sonar-deep-research","name":"Sonar Deep Research","description":"Sonar search model for autonomous research and citation-backed long-form reports","family":"sonar","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"canonical_model_id":"perplexity/sonar-deep-research","display_name":"Sonar Deep Research","type":"chat"},{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2 Contributor","type":"chat"},{"id":"upstage/solar-pro4","name":"Solar Pro 4","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.03,"output":0.12},"canonical_model_id":"upstage/solar-pro4","display_name":"Solar Pro 4","type":"chat"},{"id":"upstage/solar-pro3","name":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"upstage/solar-pro3","display_name":"Solar Pro 3","type":"chat"},{"id":"upstage/solar-pro2","name":"Solar Pro 2","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"upstage/solar-pro2","display_name":"Solar Pro 2","type":"chat"},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.1},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"mimo/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.14,"output":0.28},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"mimo/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"mistral/voxtral-small-latest","name":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/voxtral-small-latest","display_name":"Voxtral Small (latest)","type":"chat"},{"id":"qwen/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.05,"output":0.4},"canonical_model_id":"alibaba/qwen-flash","display_name":"Qwen Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32768},"cost":{"input":0.2,"output":1.6},"canonical_model_id":"alibaba/qwen3-vl-plus","display_name":"Qwen3-VL Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.2},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.2,"output":6},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1,"output":5},"canonical_model_id":"alibaba/qwen3-coder-plus","display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"alibaba":{"id":"alibaba","api":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","name":"alibaba","doc":"https://www.alibabacloud.com/help/en/model-studio/models","display_name":"alibaba","models":[{"id":"qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.05,"output":0.4},"display_name":"Qwen Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"display_name":"Qwen3.7 Max","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"qwen2-5-32b-instruct","name":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.7,"output":2.8},"display_name":"Qwen2.5 32B Instruct","type":"chat"},{"id":"qwq-plus","name":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":32768,"default":32768}},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.8,"output":2.4},"display_name":"QwQ Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.8,"output":8.4},"display_name":"Qwen2.5-VL 72B Instruct","type":"chat"},{"id":"qwen3-vl-plus","name":"Qwen3 VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":1.6,"reasoning":4.8},"display_name":"Qwen3 VL Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"display_name":"Qwen3.5 27B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.2,"output":0.4,"cache_read":0.04},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4},"display_name":"Qwen Max","search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":6},"display_name":"Qwen3 Next 80B A3B Thinking","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"],"exclusive_with":["budget_tokens"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","extra_capabilities":{"reasoning":{"supported":true,"budget":{"min":0,"max":262144,"unit":"tokens"},"effort_options":["none","low","medium","xhigh"],"continuation":["thinking_blocks"],"notes":["Prefer reasoning_effort; thinking_budget is an alternative, not an additional control.","Omitting both controls differs from explicitly selecting xhigh, which maps to 262144 budget tokens."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"xhigh"}},"type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen-plus-character-ja","name":"Qwen Plus Character (Japanese)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":512},"cost":{"input":0.5,"output":1.4},"display_name":"Qwen Plus Character (Japanese)","type":"chat"},{"id":"qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4,"reasoning":2.4},"display_name":"Qwen3.5 Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-livetranslate-flash-realtime","name":"Qwen3-LiveTranslate Flash Realtime","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":53248,"output":4096},"cost":{"input":10,"output":10,"input_audio":10,"output_audio":38},"display_name":"Qwen3-LiveTranslate Flash Realtime","type":"chat"},{"id":"qwen2-5-72b-instruct","name":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":1.4,"output":5.6},"display_name":"Qwen2.5 72B Instruct","type":"chat"},{"id":"qwen3-32b","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"display_name":"Qwen3 32B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.2,"reasoning":4},"display_name":"Qwen Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991808,"output":131072},"cost":{"input":0.03,"output":0.13,"cache_read":0.003,"cache_write":0.0375,"tiers":[{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125,"tier":{"type":"context","size":32000}},{"input":0.2,"output":0.8,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":256000}}]},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.2,"output":6},"display_name":"Qwen3 Max","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-omni-turbo-realtime","name":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-05-08","last_updated":"2025-05-08","modalities":{"input":["text","image","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.27,"output":1.07,"input_audio":4.44,"output_audio":8.89},"display_name":"Qwen-Omni Turbo Realtime","type":"chat"},{"id":"qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":1.5,"output":7.5,"tiers":[{"input":2.7,"output":13.5,"tier":{"type":"context","size":32000}},{"input":4.5,"output":22.5,"tier":{"type":"context","size":128000}}]},"display_name":"Qwen3-Coder 480B-A35B Instruct","type":"chat"},{"id":"qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.05,"output":0.2,"reasoning":0.5},"display_name":"Qwen Turbo","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":2.25,"tiers":[{"input":0.75,"output":3.75,"tier":{"type":"context","size":32000}},{"input":1.2,"output":6,"tier":{"type":"context","size":128000}}]},"display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["none","low","medium","xhigh"],"default_enabled":true,"mode":"effort","effort":"xhigh"}},"type":"chat"},{"id":"qvq-max","name":"QVQ Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qvq","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":1.2,"output":4.8},"display_name":"QVQ Max","type":"chat"},{"id":"qwen2-5-7b-instruct","name":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.175,"output":0.7},"display_name":"Qwen2.5 7B Instruct","type":"chat"},{"id":"qwen3-omni-flash","name":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.43,"output":1.66,"input_audio":3.81,"output_audio":15.11},"display_name":"Qwen3-Omni Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.8,"output":3.2},"display_name":"Qwen-VL Max","type":"chat"},{"id":"qwen3-235b-a22b","name":"Qwen3 235B A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"display_name":"Qwen3 235B A22B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-vl-30b-a3b","name":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.8,"reasoning":2.4},"display_name":"Qwen3-VL 30B-A3B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"display_name":"Qwen3.5 122B-A10B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"display_name":"Qwen3.6 35B-A3B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":2},"display_name":"Qwen3 Next 80B A3B Instruct","type":"chat"},{"id":"qwen-vl-plus","name":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.21,"output":0.63},"display_name":"Qwen-VL Plus","type":"chat"},{"id":"qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"display_name":"Qwen3.6 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5},"display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen2-5-omni-7b","name":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0.1,"output":0.4,"input_audio":6.76},"display_name":"Qwen2.5-Omni 7B","type":"chat"},{"id":"qwen-mt-plus","name":"Qwen Mt Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":2.46,"output":7.37},"display_name":"Qwen Mt Plus","type":"chat"},{"id":"qwen3-vl-235b-a22b","name":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"display_name":"Qwen3-VL 235B-A22B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":1,"output":5},"display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"qwen2-5-14b-instruct","name":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.35,"output":1.4},"display_name":"Qwen2.5 14B Instruct","type":"chat"},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"],"exclusive_with":["budget_tokens"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","extra_capabilities":{"reasoning":{"supported":true,"budget":{"min":0,"max":262144,"unit":"tokens"},"effort_options":["none","low","medium","xhigh"],"continuation":["thinking_blocks"],"notes":["Prefer reasoning_effort; thinking_budget is an alternative, not an additional control.","Omitting both controls differs from explicitly selecting xhigh, which maps to 262144 budget tokens."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"xhigh"}},"type":"chat"},{"id":"qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.35,"output":1.05},"display_name":"Qwen2.5-VL 7B Instruct","type":"chat"},{"id":"qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"display_name":"Qwen3.5 35B-A3B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.3,"output":7.8,"cache_read":0.13,"cache_write":1.625},"display_name":"Qwen3.6 Max Preview","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-mt-turbo","name":"Qwen Mt Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":0.16,"output":0.49},"display_name":"Qwen Mt Turbo","type":"chat"},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"display_name":"Qwen3.5 397B-A17B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-8b","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.18,"output":0.7,"reasoning":2.1},"display_name":"Qwen3 8B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.28,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen-omni-turbo","name":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-19","last_updated":"2025-03-26","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.07,"output":0.27,"input_audio":4.44,"output_audio":8.89},"display_name":"Qwen-Omni Turbo","type":"chat"},{"id":"qwen3-omni-flash-realtime","name":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.52,"output":1.99,"input_audio":4.57,"output_audio":18.13},"display_name":"Qwen3-Omni Flash Realtime","type":"chat"},{"id":"qwen3-asr-flash","name":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2024-04","release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":53248,"output":4096},"cost":{"input":0.035,"output":0.035},"display_name":"Qwen3-ASR Flash","type":"chat"},{"id":"qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"display_name":"Qwen3.6 27B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"display_name":"Qwen3.6 Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-14b","name":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.35,"output":1.4,"reasoning":4.2},"display_name":"Qwen3 14B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-04","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}},"display_name":"Qwen3.7 Plus","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen-vl-ocr","name":"Qwen Vl Ocr","description":"OCR model for extracting structured text from documents and screenshots","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-10-28","last_updated":"2025-04-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":34096,"output":4096},"cost":{"input":0.07,"output":0.16},"display_name":"Qwen Vl Ocr","type":"chat"},{"id":"qwen3-coder-plus-2025-09-23","name":"Qwen3 Coder Plus 2025 09 23","display_name":"Qwen3 Coder Plus 2025 09 23","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":65536},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen3-coder-plus-2025-07-22","name":"Qwen3 Coder Plus 2025 07 22","display_name":"Qwen3 Coder Plus 2025 07 22","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":65536},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-vl-ocr-latest","name":"Qwen Vl Ocr Latest","display_name":"Qwen Vl Ocr Latest","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":34096,"output":4096},"reasoning":{"supported":false},"type":"chat"},{"id":"qvq-max-2025-05-15","name":"Qvq Max 2025 05 15","display_name":"Qvq Max 2025 05 15","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":16384,"default":16384}},"type":"chat"},{"id":"qwen-long","name":"Qwen Long","display_name":"Qwen Long","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":8192},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-turbo-latest","name":"Qwen Turbo Latest","display_name":"Qwen Turbo Latest","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":38912,"default":38912}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-turbo-2024-09-19","name":"Qwen Turbo 2024 09 19","display_name":"Qwen Turbo 2024 09 19","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-flash-2025-07-28","name":"Qwen Flash 2025 07 28","display_name":"Qwen Flash 2025 07 28","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus-latest","name":"Qwen Plus Latest","display_name":"Qwen Plus Latest","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus-2024-09-19","name":"Qwen Plus 2024 09 19","display_name":"Qwen Plus 2024 09 19","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-plus-2025-07-14","name":"Qwen Plus 2025 07 14","display_name":"Qwen Plus 2025 07 14","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":38912,"default":38912}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus-2025-09-11","name":"Qwen Plus 2025 09 11","display_name":"Qwen Plus 2025 09 11","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-max-latest","name":"Qwen Max Latest","display_name":"Qwen Max Latest","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen-max-2024-09-19","name":"Qwen Max 2024 09 19","display_name":"Qwen Max 2024 09 19","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":8192},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen-max-2024-04-28","name":"Qwen Max 2024 04 28","display_name":"Qwen Max 2024 04 28","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8000,"output":2000},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-max-2024-04-03","name":"Qwen Max 2024 04 03","display_name":"Qwen Max 2024 04 03","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8000,"output":2000},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-max-2025-01-25","name":"Qwen Max 2025 01 25","display_name":"Qwen Max 2025 01 25","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3-max-2025-09-23","name":"Qwen3 Max 20250923","display_name":"Qwen3 Max 20250923","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3-max-preview","name":"Qwen3 Max Preview","display_name":"Qwen3 Max Preview","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"reasoning":{"supported":true},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","display_name":"Qwen3 235B A22B Thinking 2507","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","display_name":"Qwen3 235B A22B Instruct 2507","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","display_name":"Qwen3 30B A3B Instruct 2507","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","display_name":"Qwen3 30B A3B Thinking 2507","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","display_name":"Qwen3 30B A3B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-4b","name":"Qwen3 4B","display_name":"Qwen3 4B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-1.7b","name":"Qwen3 1.7B","display_name":"Qwen3 1.7B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":30720,"default":30720}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-0.6b","name":"Qwen3 0.6B","display_name":"Qwen3 0.6B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":30720,"default":30720}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-vl-plus-2025-09-23","name":"Qwen3 VL Plus 2025 09 23","display_name":"Qwen3 VL Plus 2025 09 23","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwq-plus-latest","name":"QwQ Plus Latest","display_name":"QwQ Plus Latest","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":32768,"default":32768}},"search":{"supported":false},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"}]},"auriko":{"id":"auriko","api":"https://api.auriko.ai/v1","name":"Auriko","doc":"https://docs.auriko.ai","display_name":"Auriko","models":[{"id":"qwen-3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.1,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat"},{"id":"minimax-m2-7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.8},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"minimax-m2-7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat"},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"unorouter":{"id":"unorouter","api":"https://api.unorouter.com/v1","name":"UnoRouter","doc":"https://unorouter.com/models","display_name":"UnoRouter","models":[{"id":"gpt-5.5:free","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat"},{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1.8,"output":10.8},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-4.5-flash:free","name":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-4.5-flash","display_name":"GLM-4.5-Flash","type":"chat"},{"id":"gemma-4-31b-it:free","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.2675,"output":5.3368},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3-ultra-550b-a55b:free","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat"},{"id":"gpt-5.4:free","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat"},{"id":"minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.819,"output":3.276},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1857,"output":1.1142},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.05,"output":8.4},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.425,"output":2.125},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1875,"output":1.125},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.44,"output":7.2},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.6001,"output":5.0288},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"step-3.7-flash:free","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0,"output":0},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"deepseek-v4-flash:free","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat"},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.2,"output":6},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"deepseek-v4-pro:free","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat"},{"id":"glm-5.2:free","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.8999,"output":1.7999},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"qwen3.5-397b-a17b:free","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m2.7:free","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.0625,"output":0.125},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"salad-cloud":{"id":"salad-cloud","name":"SaladCloud AI Gateway","doc":"https://docs.salad.com/ai-gateway/explanation/overview","display_name":"SaladCloud AI Gateway","models":[{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Qwen MoE for agentic tasks, complex reasoning, code generation, and instruction following","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.09,"output":0.6},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"vispark":{"id":"vispark","api":"https://api.lab.vispark.in/v1","name":"Vispark","doc":"https://lab.vispark.in/#vision","display_name":"Vispark","models":[{"id":"vispark/vision-large","name":"Vision Large","description":"Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-05-15","last_updated":"2026-09","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":7.37,"output":22.11},"display_name":"Vision Large","type":"chat"},{"id":"vispark/vision-small","name":"Vision Small","description":"Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-05-15","last_updated":"2026-09","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.05,"output":3.16},"display_name":"Vision Small","type":"chat"},{"id":"vispark/vision-medium","name":"Vision Medium","description":"Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-05-15","last_updated":"2026-09","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":4.21,"output":12.63},"display_name":"Vision Medium","type":"chat"}]},"siliconflow":{"id":"siliconflow","api":"https://api.siliconflow.cn/v1","name":"SiliconFlow","doc":"https://cloud.siliconflow.com/models","display_name":"SiliconFlow","models":[{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":99560},"cost":{"input":0.21,"output":0.57},"display_name":"ByteDance-Seed/Seed-OSS-36B-Instruct","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true}},"type":"chat","vision":false},{"id":"tencent/Hunyuan-A13B-Instruct","name":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":{"supported":false},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":117964},"cost":{"input":0.14,"output":0.57},"display_name":"tencent/Hunyuan-A13B-Instruct","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"Qwen/Qwen3.5-4B","name":"Qwen/Qwen3.5-4B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"display_name":"Qwen/Qwen3.5-4B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3.5-27B","name":"Qwen/Qwen3.5-27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.26,"output":2.09},"display_name":"Qwen/Qwen3.5-27B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen/Qwen3.6-35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.23,"output":1.86},"display_name":"Qwen/Qwen3.6-35B-A3B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen/Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":131072},"cost":{"input":0.13,"output":0.6},"display_name":"Qwen/Qwen3-235B-A22B-Thinking-2507","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":false},{"id":"Qwen/Qwen3-14B","name":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"cost":{"input":0.07,"output":0.28},"display_name":"Qwen/Qwen3-14B","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":false},{"id":"Qwen/Qwen3-8B","name":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"cost":{"input":0.06,"output":0.06},"display_name":"Qwen/Qwen3-8B","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":false},{"id":"Qwen/Qwen3-32B","name":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"cost":{"input":0.14,"output":0.57},"display_name":"Qwen/Qwen3-32B","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":false},{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen/Qwen3.5-35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.23,"output":1.86},"display_name":"Qwen/Qwen3.5-35B-A3B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen/Qwen3.5-122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":2.32},"display_name":"Qwen/Qwen3.5-122B-A10B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3.5-9B","name":"Qwen/Qwen3.5-9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.22,"output":1.74},"display_name":"Qwen/Qwen3.5-9B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen/Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":1.74},"display_name":"Qwen/Qwen3.5-397B-A17B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-31","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":65536},"cost":{"input":0.25,"output":1},"display_name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","metadata":{"source":"siliconflow-official-list"},"type":"code","vision":false},{"id":"Qwen/Qwen3-VL-32B-Instruct","name":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.2,"output":0.6},"display_name":"Qwen/Qwen3-VL-32B-Instruct","type":"chat"},{"id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.05,"output":0.05},"display_name":"Qwen/Qwen2.5-7B-Instruct","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-01","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":65536},"cost":{"input":0.07,"output":0.28},"display_name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","metadata":{"source":"siliconflow-official-list"},"type":"code","vision":false},{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.59,"output":0.59},"display_name":"Qwen/Qwen2.5-72B-Instruct","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","name":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.29,"output":1},"display_name":"Qwen/Qwen3-VL-30B-A3B-Thinking","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":true},{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.09,"output":0.3},"display_name":"Qwen/Qwen3-30B-A3B-Instruct-2507","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"Qwen/Qwen3-VL-32B-Thinking","name":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.2,"output":1.5},"display_name":"Qwen/Qwen3-VL-32B-Thinking","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.18,"output":0.68},"display_name":"Qwen/Qwen3-VL-8B-Instruct","type":"chat"},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.29,"output":1},"display_name":"Qwen/Qwen3-VL-30B-A3B-Instruct","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":true},{"id":"deepseek-ai/DeepSeek-R1","name":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.5,"output":2.18},"display_name":"deepseek-ai/DeepSeek-R1","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":false},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"},{"id":"deepseek-ai/DeepSeek-OCR","name":"deepseek-ai/DeepSeek-OCR","description":"OCR model for extracting structured text from documents and screenshots","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":3113},"cost":{"input":0,"output":0},"display_name":"deepseek-ai/DeepSeek-OCR","metadata":{"source":"siliconflow-official-list"},"type":"image","vision":true},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"deepseek-ai/DeepSeek-V4-Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":393000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"display_name":"deepseek-ai/DeepSeek-V4-Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.2","name":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":65536},"cost":{"input":0.27,"output":0.42},"display_name":"deepseek-ai/DeepSeek-V3.2","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.27,"output":1},"display_name":"deepseek-ai/DeepSeek-V3.1-Terminus","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"deepseek-ai/DeepSeek-V3","name":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.25,"output":1},"display_name":"deepseek-ai/DeepSeek-V3","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"stepfun-ai/Step-3.5-Flash","name":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","family":"step","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":256000},"cost":{"input":0.1,"output":0.3},"display_name":"stepfun-ai/Step-3.5-Flash","type":"chat"},{"id":"inclusionAI/Ling-flash-2.0","name":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":49780},"cost":{"input":0.14,"output":0.57},"display_name":"inclusionAI/Ling-flash-2.0","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":262000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"zai-org/GLM-4.5-Air","name":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":98304},"cost":{"input":0.14,"output":0.86},"display_name":"zai-org/GLM-4.5-Air","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"Pro/deepseek-ai/DeepSeek-R1","name":"Pro/deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.5,"output":2.18},"display_name":"Pro/deepseek-ai/DeepSeek-R1","metadata":{"source":"siliconflow-official-list"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat","vision":false},{"id":"Pro/deepseek-ai/DeepSeek-V3.2","name":"Pro/deepseek-ai/DeepSeek-V3.2","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":65536},"cost":{"input":0.27,"output":0.42},"display_name":"Pro/deepseek-ai/DeepSeek-V3.2","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"Pro/deepseek-ai/DeepSeek-V3","name":"Pro/deepseek-ai/DeepSeek-V3","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.25,"output":1},"display_name":"Pro/deepseek-ai/DeepSeek-V3","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"Pro/deepseek-ai/DeepSeek-V3.1-Terminus","name":"Pro/deepseek-ai/DeepSeek-V3.1-Terminus","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":8192},"cost":{"input":0.27,"output":1},"display_name":"Pro/deepseek-ai/DeepSeek-V3.1-Terminus","metadata":{"source":"siliconflow-official-list"},"type":"chat","vision":false},{"id":"Pro/MiniMaxAI/MiniMax-M2.5","name":"Pro/MiniMaxAI/MiniMax-M2.5","description":"Frontier MiniMax model for engineering, office tasks, and agentic reasoning","family":"minimax","attachment":false,"reasoning":{"supported":true},"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":131000},"cost":{"input":0.3,"output":1.22},"display_name":"Pro/MiniMaxAI/MiniMax-M2.5","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"Pro/moonshotai/Kimi-K2.6","name":"Pro/moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":99560},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"Pro/moonshotai/Kimi-K2.6","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"Pro/moonshotai/Kimi-K2.5","name":"Pro/moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":99560},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"display_name":"Pro/moonshotai/Kimi-K2.5","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"Pro/zai-org/GLM-5.1","name":"Pro/zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"display_name":"Pro/zai-org/GLM-5.1","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"Pro/zai-org/GLM-5","name":"Pro/zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":131072},"cost":{"input":1,"output":3.2},"display_name":"Pro/zai-org/GLM-5","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"PaddlePaddle/PaddleOCR-VL-1.5","name":"PaddlePaddle/PaddleOCR-VL-1.5","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-29","last_updated":"2026-01-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":6226},"cost":{"input":0,"output":0},"display_name":"PaddlePaddle/PaddleOCR-VL-1.5","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"deepseek-ai/DeepSeek-V3.2-Exp","display_name":"deepseek-ai/DeepSeek-V3.2-Exp","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/deepseek-ai/DeepSeek-V3.2-Exp","name":"Pro/deepseek-ai/DeepSeek-V3.2-Exp","display_name":"Pro/deepseek-ai/DeepSeek-V3.2-Exp","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"inclusionAI/Ring-1T","name":"inclusionAI/Ring-1T","display_name":"inclusionAI/Ring-1T","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionAI/Ling-1T","name":"inclusionAI/Ling-1T","display_name":"inclusionAI/Ling-1T","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"zai-org/GLM-4.6","name":"zai-org/GLM-4.6","display_name":"zai-org/GLM-4.6","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen/Qwen3-VL-235B-A22B-Instruct","display_name":"Qwen/Qwen3-VL-235B-A22B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true},{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","name":"Qwen/Qwen3-VL-235B-A22B-Thinking","display_name":"Qwen/Qwen3-VL-235B-A22B-Thinking","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Omni-30B-A3B-Instruct","name":"Qwen/Qwen3-Omni-30B-A3B-Instruct","display_name":"Qwen/Qwen3-Omni-30B-A3B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen3-Omni-30B-A3B-Thinking","name":"Qwen/Qwen3-Omni-30B-A3B-Thinking","display_name":"Qwen/Qwen3-Omni-30B-A3B-Thinking","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Omni-30B-A3B-Captioner","name":"Qwen/Qwen3-Omni-30B-A3B-Captioner","display_name":"Qwen/Qwen3-Omni-30B-A3B-Captioner","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"moonshotai/Kimi-K2-Instruct-0905","display_name":"moonshotai/Kimi-K2-Instruct-0905","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/moonshotai/Kimi-K2-Instruct-0905","name":"Pro/moonshotai/Kimi-K2-Instruct-0905","display_name":"Pro/moonshotai/Kimi-K2-Instruct-0905","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen/Qwen3-Next-80B-A3B-Instruct","display_name":"Qwen/Qwen3-Next-80B-A3B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen/Qwen3-Next-80B-A3B-Thinking","display_name":"Qwen/Qwen3-Next-80B-A3B-Thinking","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"inclusionAI/Ring-flash-2.0","name":"inclusionAI/Ring-flash-2.0","display_name":"inclusionAI/Ring-flash-2.0","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionAI/Ling-mini-2.0","name":"inclusionAI/Ling-mini-2.0","display_name":"inclusionAI/Ling-mini-2.0","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen-Image-Edit-2509","name":"Qwen/Qwen-Image-Edit-2509","display_name":"Qwen/Qwen-Image-Edit-2509","type":"image-edit","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"Qwen/Qwen-Image-Edit","name":"Qwen/Qwen-Image-Edit","display_name":"Qwen/Qwen-Image-Edit","type":"image-edit","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"Qwen/Qwen-Image","name":"Qwen/Qwen-Image","display_name":"Qwen/Qwen-Image","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"tencent/Hunyuan-MT-7B","name":"tencent/Hunyuan-MT-7B","display_name":"tencent/Hunyuan-MT-7B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Wan-AI/Wan2.2-I2V-A14B","name":"Wan-AI/Wan2.2-I2V-A14B","display_name":"Wan-AI/Wan2.2-I2V-A14B","type":"video","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"],"output":["video"]},"limit":{"context":null,"output":null}},{"id":"Wan-AI/Wan2.2-T2V-A14B","name":"Wan-AI/Wan2.2-T2V-A14B","display_name":"Wan-AI/Wan2.2-T2V-A14B","type":"video","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["video"]},"limit":{"context":null,"output":null}},{"id":"zai-org/GLM-4.5V","name":"zai-org/GLM-4.5V","display_name":"zai-org/GLM-4.5V","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"zai-org/GLM-4.5","name":"zai-org/GLM-4.5","display_name":"zai-org/GLM-4.5","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"stepfun-ai/step3","name":"stepfun-ai/step3","display_name":"stepfun-ai/step3","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"TeleAI/TeleSpeechASR","name":"TeleAI/TeleSpeechASR","display_name":"TeleAI/TeleSpeechASR","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"],"output":["text"]},"limit":{"context":null,"output":null}},{"id":"Qwen/Qwen3-30B-A3B-Thinking-2507","name":"Qwen/Qwen3-30B-A3B-Thinking-2507","display_name":"Qwen/Qwen3-30B-A3B-Thinking-2507","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen/Qwen3-235B-A22B-Instruct-2507","display_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"THUDM/GLM-4.1V-9B-Thinking","name":"THUDM/GLM-4.1V-9B-Thinking","display_name":"THUDM/GLM-4.1V-9B-Thinking","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/THUDM/GLM-4.1V-9B-Thinking","name":"Pro/THUDM/GLM-4.1V-9B-Thinking","display_name":"Pro/THUDM/GLM-4.1V-9B-Thinking","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"baidu/ERNIE-4.5-300B-A47B","name":"baidu/ERNIE-4.5-300B-A47B","display_name":"baidu/ERNIE-4.5-300B-A47B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]}},{"id":"moonshotai/Kimi-Dev-72B","name":"moonshotai/Kimi-Dev-72B","display_name":"moonshotai/Kimi-Dev-72B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"MiniMaxAI/MiniMax-M1-80k","name":"MiniMaxAI/MiniMax-M1-80k","display_name":"MiniMaxAI/MiniMax-M1-80k","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Tongyi-Zhiwen/QwenLong-L1-32B","name":"Tongyi-Zhiwen/QwenLong-L1-32B","display_name":"Tongyi-Zhiwen/QwenLong-L1-32B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","name":"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","display_name":"deepseek-ai/DeepSeek-R1-0528-Qwen3-8B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen/Qwen3-30B-A3B","display_name":"Qwen/Qwen3-30B-A3B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Reranker-8B","name":"Qwen/Qwen3-Reranker-8B","display_name":"Qwen/Qwen3-Reranker-8B","type":"rerank","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["score"]},"limit":{"context":8192,"output":2048}},{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen/Qwen3-Embedding-8B","display_name":"Qwen/Qwen3-Embedding-8B","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["embedding"]},"limit":{"context":8192,"output":2048}},{"id":"Qwen/Qwen3-Reranker-4B","name":"Qwen/Qwen3-Reranker-4B","display_name":"Qwen/Qwen3-Reranker-4B","type":"rerank","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["score"]},"limit":{"context":8192,"output":2048}},{"id":"Qwen/Qwen3-Embedding-4B","name":"Qwen/Qwen3-Embedding-4B","display_name":"Qwen/Qwen3-Embedding-4B","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["embedding"]},"limit":{"context":8192,"output":2048}},{"id":"Qwen/Qwen3-Reranker-0.6B","name":"Qwen/Qwen3-Reranker-0.6B","display_name":"Qwen/Qwen3-Reranker-0.6B","type":"rerank","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["score"]},"limit":{"context":8192,"output":2048}},{"id":"Qwen/Qwen3-Embedding-0.6B","name":"Qwen/Qwen3-Embedding-0.6B","display_name":"Qwen/Qwen3-Embedding-0.6B","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["embedding"]},"limit":{"context":8192,"output":2048}},{"id":"ascend-tribe/pangu-pro-moe","name":"ascend-tribe/pangu-pro-moe","display_name":"ascend-tribe/pangu-pro-moe","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"THUDM/GLM-Z1-32B-0414","name":"THUDM/GLM-Z1-32B-0414","display_name":"THUDM/GLM-Z1-32B-0414","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"THUDM/GLM-4-32B-0414","name":"THUDM/GLM-4-32B-0414","display_name":"THUDM/GLM-4-32B-0414","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"THUDM/GLM-Z1-9B-0414","name":"THUDM/GLM-Z1-9B-0414","display_name":"THUDM/GLM-Z1-9B-0414","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"THUDM/GLM-4-9B-0414","name":"THUDM/GLM-4-9B-0414","display_name":"THUDM/GLM-4-9B-0414","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen/Qwen2.5-VL-32B-Instruct","display_name":"Qwen/Qwen2.5-VL-32B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen3-235B-A22B","name":"Qwen/Qwen3-235B-A22B","display_name":"Qwen/Qwen3-235B-A22B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/QwQ-32B","name":"Qwen/QwQ-32B","display_name":"Qwen/QwQ-32B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen/Qwen2.5-VL-72B-Instruct","display_name":"Qwen/Qwen2.5-VL-72B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/Qwen/Qwen2.5-VL-7B-Instruct","name":"Pro/Qwen/Qwen2.5-VL-7B-Instruct","display_name":"Pro/Qwen/Qwen2.5-VL-7B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/QVQ-72B-Preview","name":"Qwen/QVQ-72B-Preview","display_name":"Qwen/QVQ-72B-Preview","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"deepseek-ai/DeepSeek-V2.5","name":"deepseek-ai/DeepSeek-V2.5","display_name":"deepseek-ai/DeepSeek-V2.5","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"fnlp/MOSS-TTSD-v0.5","name":"fnlp/MOSS-TTSD-v0.5","display_name":"fnlp/MOSS-TTSD-v0.5","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["audio"]},"limit":{"context":null,"output":null}},{"id":"FunAudioLLM/CosyVoice2-0.5B","name":"FunAudioLLM/CosyVoice2-0.5B","display_name":"FunAudioLLM/CosyVoice2-0.5B","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["audio"]},"limit":{"context":null,"output":null}},{"id":"FunAudioLLM/SenseVoiceSmall","name":"FunAudioLLM/SenseVoiceSmall","display_name":"FunAudioLLM/SenseVoiceSmall","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"],"output":["text"]},"limit":{"context":null,"output":null}},{"id":"IndexTeam/IndexTTS-2","name":"IndexTeam/IndexTTS-2","display_name":"IndexTeam/IndexTTS-2","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["audio"]},"limit":{"context":null,"output":null}},{"id":"BAAI/bge-m3","name":"BAAI/bge-m3","display_name":"BAAI/bge-m3","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"BAAI/bge-reranker-v2-m3","name":"BAAI/bge-reranker-v2-m3","display_name":"BAAI/bge-reranker-v2-m3","type":"rerank","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["score"]},"limit":{"context":8192,"output":2048}},{"id":"netease-youdao/bce-embedding-base_v1","name":"netease-youdao/bce-embedding-base_v1","display_name":"netease-youdao/bce-embedding-base_v1","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["embedding"]},"limit":{"context":8192,"output":2048}},{"id":"netease-youdao/bce-reranker-base_v1","name":"netease-youdao/bce-reranker-base_v1","display_name":"netease-youdao/bce-reranker-base_v1","type":"reranker","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["score"]},"limit":{"context":8192,"output":2048}},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen/Qwen2.5-Coder-32B-Instruct","display_name":"Qwen/Qwen2.5-Coder-32B-Instruct","type":"code","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Kwai-Kolors/Kolors","name":"Kwai-Kolors/Kolors","display_name":"Kwai-Kolors/Kolors","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"Qwen/Qwen2-VL-72B-Instruct","name":"Qwen/Qwen2-VL-72B-Instruct","display_name":"Qwen/Qwen2-VL-72B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen2.5-72B-Instruct-128K","name":"Qwen/Qwen2.5-72B-Instruct-128K","display_name":"Qwen/Qwen2.5-72B-Instruct-128K","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"deepseek-ai/deepseek-vl2","name":"deepseek-ai/deepseek-vl2","display_name":"deepseek-ai/deepseek-vl2","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen2.5-32B-Instruct","name":"Qwen/Qwen2.5-32B-Instruct","display_name":"Qwen/Qwen2.5-32B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen2.5-14B-Instruct","name":"Qwen/Qwen2.5-14B-Instruct","display_name":"Qwen/Qwen2.5-14B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen2.5-Coder-7B-Instruct","name":"Qwen/Qwen2.5-Coder-7B-Instruct","display_name":"Qwen/Qwen2.5-Coder-7B-Instruct","type":"code","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"internlm/internlm2_5-7b-chat","name":"internlm/internlm2_5-7b-chat","display_name":"internlm/internlm2_5-7b-chat","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Qwen/Qwen2-7B-Instruct","name":"Qwen/Qwen2-7B-Instruct","display_name":"Qwen/Qwen2-7B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"THUDM/glm-4-9b-chat","name":"THUDM/glm-4-9b-chat","display_name":"THUDM/glm-4-9b-chat","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"BAAI/bge-large-en-v1.5","name":"BAAI/bge-large-en-v1.5","display_name":"BAAI/bge-large-en-v1.5","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"BAAI/bge-large-zh-v1.5","name":"BAAI/bge-large-zh-v1.5","display_name":"BAAI/bge-large-zh-v1.5","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"LoRA/Qwen/Qwen2.5-32B-Instruct","name":"LoRA/Qwen/Qwen2.5-32B-Instruct","display_name":"LoRA/Qwen/Qwen2.5-32B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"LoRA/Qwen/Qwen2.5-14B-Instruct","name":"LoRA/Qwen/Qwen2.5-14B-Instruct","display_name":"LoRA/Qwen/Qwen2.5-14B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","name":"Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","display_name":"Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/Qwen/Qwen2.5-Coder-7B-Instruct","name":"Pro/Qwen/Qwen2.5-Coder-7B-Instruct","display_name":"Pro/Qwen/Qwen2.5-Coder-7B-Instruct","type":"code","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/BAAI/bge-m3","name":"Pro/BAAI/bge-m3","display_name":"Pro/BAAI/bge-m3","type":"embedding","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/Qwen/Qwen2.5-7B-Instruct","name":"Pro/Qwen/Qwen2.5-7B-Instruct","display_name":"Pro/Qwen/Qwen2.5-7B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/BAAI/bge-reranker-v2-m3","name":"Pro/BAAI/bge-reranker-v2-m3","display_name":"Pro/BAAI/bge-reranker-v2-m3","type":"rerank","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["score"]},"limit":{"context":8192,"output":2048}},{"id":"LoRA/Qwen/Qwen2.5-72B-Instruct","name":"LoRA/Qwen/Qwen2.5-72B-Instruct","display_name":"LoRA/Qwen/Qwen2.5-72B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/Qwen/Qwen2-7B-Instruct","name":"Pro/Qwen/Qwen2-7B-Instruct","display_name":"Pro/Qwen/Qwen2-7B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"LoRA/Qwen/Qwen2.5-7B-Instruct","name":"LoRA/Qwen/Qwen2.5-7B-Instruct","display_name":"LoRA/Qwen/Qwen2.5-7B-Instruct","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"Pro/THUDM/glm-4-9b-chat","name":"Pro/THUDM/glm-4-9b-chat","display_name":"Pro/THUDM/glm-4-9b-chat","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"THUDM/GLM-Z1-Rumination-32B-0414","name":"THUDM/GLM-Z1-Rumination-32B-0414","display_name":"THUDM/GLM-Z1-Rumination-32B-0414","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}},{"id":"stabilityai/stable-diffusion-xl-base-1.0","name":"stabilityai/stable-diffusion-xl-base-1.0","display_name":"stabilityai/stable-diffusion-xl-base-1.0","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"black-forest-labs/FLUX.1-schnell","name":"black-forest-labs/FLUX.1-schnell","display_name":"black-forest-labs/FLUX.1-schnell","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"black-forest-labs/FLUX.1-dev","name":"black-forest-labs/FLUX.1-dev","display_name":"black-forest-labs/FLUX.1-dev","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"Pro/black-forest-labs/FLUX.1-schnell","name":"Pro/black-forest-labs/FLUX.1-schnell","display_name":"Pro/black-forest-labs/FLUX.1-schnell","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"stabilityai/stable-diffusion-3-5-large","name":"stabilityai/stable-diffusion-3-5-large","display_name":"stabilityai/stable-diffusion-3-5-large","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"fishaudio/fish-speech-1.4","name":"fishaudio/fish-speech-1.4","display_name":"fishaudio/fish-speech-1.4","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["audio"]},"limit":{"context":null,"output":null}},{"id":"RVC-Boss/GPT-SoVITS","name":"RVC-Boss/GPT-SoVITS","display_name":"RVC-Boss/GPT-SoVITS","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["audio"]},"limit":{"context":null,"output":null}},{"id":"fishaudio/fish-speech-1.5","name":"fishaudio/fish-speech-1.5","display_name":"fishaudio/fish-speech-1.5","type":"audio","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["audio"]},"limit":{"context":null,"output":null}},{"id":"black-forest-labs/FLUX.1-pro","name":"black-forest-labs/FLUX.1-pro","display_name":"black-forest-labs/FLUX.1-pro","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"LoRA/black-forest-labs/FLUX.1-dev","name":"LoRA/black-forest-labs/FLUX.1-dev","display_name":"LoRA/black-forest-labs/FLUX.1-dev","type":"image","metadata":{"source":"siliconflow-official-list"},"vision":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"limit":{"context":null,"output":null}},{"id":"SeedLLM/Seed-Rice-7B","name":"SeedLLM/Seed-Rice-7B","display_name":"SeedLLM/Seed-Rice-7B","type":"chat","metadata":{"source":"siliconflow-official-list"},"vision":false,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192}}],"metadata":{"source":"public-provider-conf-template"}},"regolo-ai":{"id":"regolo-ai","api":"https://api.regolo.ai/v1","name":"Regolo AI","doc":"https://docs.regolo.ai/","display_name":"Regolo AI","models":[{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":120000,"output":120000},"cost":{"input":0.58,"output":2.42},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"brick-v1-beta","name":"Brick v1 Beta","description":"Semantic router by Regolo.ai that directs each request to the most suitable model, optimizing costs and performance","family":"model-router","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":100000,"output":15000},"status":"beta","cost":{"input":0,"output":0},"display_name":"Brick v1 Beta","type":"chat"},{"id":"qwen3.5-122b","name":"Qwen3.5-122B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.9,"output":3.6},"display_name":"Qwen3.5-122B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-coder-next","name":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.3,"output":1.2},"display_name":"Qwen3-Coder-Next","type":"chat"},{"id":"apertus-70b","name":"Apertus 70B","description":"Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":30000,"output":30000},"cost":{"input":0.46,"output":2.42},"canonical_model_id":"swiss-ai/apertus-70b","display_name":"Apertus 70B","type":"chat"},{"id":"glm5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":96000,"output":96000},"cost":{"input":2.31,"output":6},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"qwen3-reranker-4b","name":"Qwen3-Reranker-4B","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.12,"output":0.12},"display_name":"Qwen3-Reranker-4B","type":"rerank"},{"id":"deepseek-ocr-2","name":"DeepSeek OCR 2","description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":4000,"output":4000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-ocr-2","display_name":"DeepSeek OCR 2","type":"chat"},{"id":"llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.6,"output":2.7},"display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"gemma4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"output":100000},"cost":{"input":0.46,"output":2.42},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"brick-complexity-pro","name":"Brick Complexity Pro","description":"Complexity classifier that powers the Brick semantic router by extracting query difficulty","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":100000,"output":15000},"cost":{"input":0.12,"output":0.46},"display_name":"Brick Complexity Pro","type":"chat"},{"id":"gpt-oss-20b","name":"GPT-OSS-20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.4,"output":1.8},"display_name":"GPT-OSS-20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-9b","name":"Qwen3.5-9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.6},"display_name":"Qwen3.5-9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-embedding-8b","name":"Qwen3-Embedding-8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.1,"output":0.1},"display_name":"Qwen3-Embedding-8B","type":"embedding"},{"id":"mistral-small-4-119b","name":"Mistral Small 4 119B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-15","last_updated":"2026-03-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":0.75,"output":3},"display_name":"Mistral Small 4 119B","type":"chat"},{"id":"qwen-image","name":"Qwen-Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.5,"output":2},"display_name":"Qwen-Image","type":"image-generation"},{"id":"gpt-oss-120b","name":"GPT-OSS-120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1,"output":4.2},"display_name":"GPT-OSS-120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"faster-whisper-large-v3","name":"Faster Whisper Large v3","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":4096},"cost":{"input":0,"output":0},"canonical_model_id":"openai/whisper-large-v3","display_name":"Faster Whisper Large v3","type":"chat"}]},"xiaomi-token-plan-ams":{"id":"xiaomi-token-plan-ams","api":"https://token-plan-ams.xiaomimimo.com/v1","name":"Xiaomi Token Plan (Europe)","doc":"https://platform.xiaomimimo.com/#/docs","display_name":"Xiaomi Token Plan (Europe)","models":[{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS-VoiceClone","type":"chat"},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2-tts","name":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2-TTS","type":"chat"},{"id":"mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2-pro","display_name":"MiMo-V2-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-tts","name":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS","type":"chat"},{"id":"mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS-VoiceDesign","type":"chat"},{"id":"mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"inceptron":{"id":"inceptron","api":"https://api.inceptron.io/v1","name":"Inceptron","doc":"https://docs.inceptron.io","display_name":"Inceptron","models":[{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.13,"output":0.28,"cache_read":0.03,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.53,"output":3.39,"cache_read":0.17,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.66,"output":3.4,"cache_read":0.18,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.71,"output":2.35,"cache_read":0.12,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"aimlapi":{"id":"aimlapi","api":"https://api.aimlapi.com/v1","name":"AI/ML API","doc":"https://docs.aimlapi.com","display_name":"AI/ML API","models":[{"id":"sao10k/l3-lunaris-8b","name":"Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-13","last_updated":"2024-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":7372},"cost":{"input":0.06877,"output":0.06877},"canonical_model_id":"sao10k/l3-lunaris-8b","display_name":"Llama 3 8B Lunaris","type":"chat"},{"id":"sao10k/l3.3-euryale-70b","name":"Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-12-18","last_updated":"2024-12-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.89401,"output":1.03155},"canonical_model_id":"sao10k/l3.3-euryale-70b","display_name":"Llama 3.3 Euryale 70B","type":"chat"},{"id":"sao10k/l3.1-euryale-70b","name":"Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-28","last_updated":"2024-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":1.99488,"output":1.99488},"canonical_model_id":"sao10k/l3.1-euryale-70b","display_name":"Llama 3.1 Euryale 70B v2.2","type":"chat"},{"id":"bytedance-seed/seed-1.6-flash","name":"Seed 1.6 Flash","description":"Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.103155,"output":0.41262},"canonical_model_id":"bytedance-seed/seed-1-6-flash","display_name":"Seed 1.6 Flash","type":"chat"},{"id":"bytedance-seed/seed-2.0-lite","name":"Seed-2.0-Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.34385,"output":2.7508},"canonical_model_id":"bytedance-seed/seed-2.0-lite","display_name":"Seed-2.0-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bytedance-seed/seed-2.0-mini","name":"Seed-2.0-Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.13754,"output":0.55016},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed-2.0-Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bytedance-seed/seed-2.0-code","name":"Seed-2.0-Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.6877,"output":4.1262},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed-2.0-Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"anthropic/claude-opus-4.5","name":"Claude 4.5 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":6.877,"output":34.385,"cache_read":0.6877},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude 4.5 Opus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude 4.7 Opus","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6.877,"output":34.385,"cache_read":0.6877},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude 4.7 Opus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.13,"output":0.65,"cache_read":0.013},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-opus-4.8","name":"Claude 4.8 Opus","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6.877,"output":34.385,"cache_read":0.6877},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude 4.8 Opus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Claude 4.5 Haiku","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.3754,"output":6.877,"cache_read":0.13754},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude 4.5 Haiku","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6.5,"output":32.5,"cache_read":0.65},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.26},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":13,"output":65,"cache_read":0.325},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-4.5","name":"Claude 4.5 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":4.1262,"output":20.631,"cache_read":0.41262},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude 4.5 Sonnet","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":13,"output":65,"cache_read":1.3},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.26},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude 4.6 Sonnet","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":4.1262,"output":20.631,"cache_read":0.41262},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude 4.6 Sonnet","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.2,"output":26,"cache_read":0.26},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"cohere/command-r-08-2024","name":"Command R (08-2024)","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.20631,"output":0.82524},"canonical_model_id":"cohere/command-r-08-2024","display_name":"Command R (08-2024)","type":"chat"},{"id":"cohere/command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":3.4385,"output":13.754},"canonical_model_id":"cohere/command-a","display_name":"Command A","type":"chat"},{"id":"cohere/command-r7b-12-2024","name":"Command R7B (12-2024)","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.051578,"output":0.20631},"canonical_model_id":"cohere/command-r7b-12-2024","display_name":"Command R7B (12-2024)","type":"chat"},{"id":"cohere/command-r-plus-08-2024","name":"Command R+ (08-2024)","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":3.4385,"output":13.754},"canonical_model_id":"cohere/command-r-plus-08-2024","display_name":"Command R+ (08-2024)","type":"chat"},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.39,"output":1.56,"cache_read":0.0078},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.572,"output":1.716,"cache_read":0.0182},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.39,"output":1.56,"cache_read":0.0078},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":2.393196,"output":4.786392,"cache_read":0.199433},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07-31","release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":124000},"cost":{"input":0.398866,"output":1.567956,"cache_read":0.192556},"canonical_model_id":"deepseek/deepseek-chat-v3-0324","display_name":"DeepSeek V3","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.17,"output":3.51,"cache_read":0.039},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.39,"output":1.56,"cache_read":0.0078},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"unbiased/pareto","name":"Pareto","description":"Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":3.4385,"output":10.3155,"cache_read":0.34385},"canonical_model_id":"unbiased/pareto","display_name":"Pareto","type":"chat"},{"id":"tencent/hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.10178,"output":0.405743},"canonical_model_id":"tencent/hy-mt2-30b-a3b","display_name":"Hy-MT2-30B-A3B","type":"chat"},{"id":"tencent/hy-mt2-1.8b","name":"Hy-MT2-1.8B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.060518,"output":0.243446},"canonical_model_id":"tencent/hy-mt2-1.8b","display_name":"Hy-MT2-1.8B","type":"chat"},{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.27508,"output":1.10032,"cache_read":0.06877},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"tencent/hy-mt2-7b","name":"Hy-MT2-7B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-19","last_updated":"2026-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.10178,"output":0.405743},"canonical_model_id":"tencent/hy-mt2-7b","display_name":"Hy-MT2-7B","type":"chat"},{"id":"tencent/hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":1.147084,"output":3.439875,"cache_read":0.057767},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":16384},"cost":{"input":4.1262,"output":6.877},"canonical_model_id":"anthracite-org/magnum-v4-72b","display_name":"Magnum v4 72B","type":"chat"},{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"Llama 3.3 70B Instruct Turbo","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":127000},"cost":{"input":1.352,"output":1.352},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct Turbo","type":"chat"},{"id":"z-ai/glm-4.6v","name":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.41262,"output":1.23786,"cache_read":0.075647},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM 4.6V","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5v-turbo","name":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.56,"output":5.2,"cache_read":0.312},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM 5V Turbo","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.195,"output":0.65,"cache_read":0.039},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-4.5v","name":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.82524,"output":2.47572,"cache_read":0.151294},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM 4.5V","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.171925,"output":0.6877,"cache_read":0.013754},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM 4.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5-turbo","name":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":1.56,"output":5.2,"cache_read":0.312},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM 5 Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inference-net/schematron-v2-small","name":"Schematron V2 Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-09-12","last_updated":"2026-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.06877,"output":0.316342},"canonical_model_id":"inference-net/schematron-v2-small","display_name":"Schematron V2 Small","type":"chat"},{"id":"inference-net/schematron-v2-turbo","name":"Schematron V2 Turbo","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-09-12","last_updated":"2026-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.041262,"output":0.20631},"canonical_model_id":"inference-net/schematron-v2-turbo","display_name":"Schematron V2 Turbo","type":"chat"},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":262144},"cost":{"input":0.797732,"output":1.980576,"cache_read":0.159546},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.3754,"output":5.57037,"cache_read":0.233818},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"perplexity/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":3.9,"output":19.5},"canonical_model_id":"perplexity/sonar-pro","display_name":"Sonar Pro","type":"chat"},{"id":"perplexity/sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":100000},"cost":{"input":1.3,"output":1.3},"canonical_model_id":"perplexity/sonar","display_name":"Sonar","type":"chat"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.71925,"output":5.84545,"cache_read":0.20631},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.48139,"output":2.0631,"cache_read":0.055016},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.71925,"output":5.84545,"cache_read":0.20631},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.71925,"output":5.84545,"cache_read":0.20631},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-18","last_updated":"2024-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.96278,"output":0.96278},"canonical_model_id":"nousresearch/hermes-3-llama-3.1-70b","display_name":"Hermes 3 70B Instruct","type":"chat"},{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-16","last_updated":"2024-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":1.3754,"output":1.3754},"canonical_model_id":"nousresearch/hermes-3-llama-3.1-405b","display_name":"Hermes 3 405B Instruct","type":"chat"},{"id":"alibaba/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.61893,"output":4.40128},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":52429},"cost":{"input":3.4385,"output":8.59625,"cache_read":0.6877},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"alibaba/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"cost":{"input":2.08,"output":8.32,"cache_read":0.416},"canonical_model_id":"alibaba/qwen-max","display_name":"Qwen Max","type":"chat"},{"id":"alibaba/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.6,"output":7.8,"cache_read":0.325},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"alibaba/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":16384},"cost":{"input":0.52,"output":1.56,"cache_read":0.104},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":1.3754,"output":6.705075,"cache_read":1.3754},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3 Coder","type":"chat"},{"id":"alibaba/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":129024,"output":16384},"cost":{"input":0.20631,"output":1.65048},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3 Next 80B A3B Instruct","type":"chat"},{"id":"alibaba/qwen3.8-max-prime","name":"Qwen3.8 Max Prime","description":"High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows","family":"qwen3.8-max","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":5.5016,"output":16.5048,"cache_read":0.6877},"canonical_model_id":"alibaba/qwen3.8-max-prime","display_name":"Qwen3.8 Max Prime","type":"chat"},{"id":"alibaba/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.208,"output":0.611,"cache_read":0.0208},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","name":"Venice Uncensored","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04-30","release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.27508,"output":1.23786},"canonical_model_id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","display_name":"Venice Uncensored","type":"chat"},{"id":"thedrummer/skyfall-36b-v2","name":"Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2025-03-10","last_updated":"2025-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.75647,"output":1.10032,"cache_read":0.34385},"canonical_model_id":"thedrummer/skyfall-36b-v2","display_name":"Skyfall 36B V2","type":"chat"},{"id":"thedrummer/unslopnemo-12b","name":"UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-04-30","release_date":"2024-11-08","last_updated":"2024-11-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.55016,"output":0.55016},"canonical_model_id":"thedrummer/unslopnemo-12b","display_name":"UnslopNemo 12B","type":"chat"},{"id":"thedrummer/cydonia-24b-v4.1","name":"Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-04-30","release_date":"2025-09-27","last_updated":"2025-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.41262,"output":0.6877,"cache_read":0.20631},"canonical_model_id":"thedrummer/cydonia-24b-v4.1","display_name":"Cydonia 24B V4.1","type":"chat"},{"id":"x-ai/grok-4-fast-non-reasoning","name":"Grok 4 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":1999000},"cost":{"input":1.625,"output":3.25,"cache_read":0.26},"canonical_model_id":"xai/grok-4-fast-non-reasoning","display_name":"Grok 4 Fast Non-Reasoning","type":"chat"},{"id":"x-ai/grok-4-20-0309-non-reasoning","name":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":1999000},"cost":{"input":1.625,"output":3.25,"cache_read":0.26},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 Non-Reasoning","type":"chat"},{"id":"upstage/solar-pro-3","name":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.20631,"output":0.82524,"cache_read":0.020631},"canonical_model_id":"upstage/solar-pro3","display_name":"Solar Pro 3","type":"chat"},{"id":"upstage/solar-pro4","name":"Solar Pro 4","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.041262,"output":0.165048,"cache_read":0.008252},"canonical_model_id":"upstage/solar-pro4","display_name":"Solar Pro 4","type":"chat"},{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2.0631,"output":12.3786,"cache_read":0.20631},"canonical_model_id":"google/gemini-flash-latest","display_name":"Gemini Flash Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B Instruct","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":1.361646,"output":2.049346,"cache_read":1.361646},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B Instruct","type":"chat"},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":117964},"cost":{"input":0.20631,"output":0.632684,"cache_read":0.103155},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B","type":"chat"},{"id":"google/gemma-2-27b-it","name":"Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-07-13","last_updated":"2024-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"cost":{"input":0.89401,"output":0.89401},"canonical_model_id":"google/gemma-2-27b-it","display_name":"Gemma 2 27B","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.95,"output":9.75,"cache_read":0.195},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.20631,"output":0.82524,"cache_read":0.20631},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.6,"output":15.6,"cache_read":0.65},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":96000},"cost":{"input":0.06877,"output":0.20631,"cache_read":0.055016},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B","type":"chat"},{"id":"google/gemini-3-8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.975,"output":4.875,"cache_read":0.0975},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat"},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.975,"output":4.875,"cache_read":0.0975},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"output":65536},"cost":{"input":2.7508,"output":16.5048,"cache_read":0.27508},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.975,"output":4.875,"cache_read":0.0975},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":32768},"cost":{"input":0.06877,"output":0.13754,"cache_read":0.055016},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B","type":"chat"},{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.34385,"output":2.0631,"cache_read":0.034385},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"ibm-granite/granite-4.0-h-micro","name":"Granite 4.0 Micro","description":"Compact open-weight hybrid Granite model for lightweight enterprise chat and tool calling","family":"granite","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.023382,"output":0.154045},"canonical_model_id":"ibm/granite-4-h-micro","display_name":"Granite 4.0 Micro","type":"chat"},{"id":"mistralai/mistral-nemo","name":"Mistral NeMo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.20631,"output":0.233818,"cache_read":0.20631},"canonical_model_id":"mistral/mistral-nemo","display_name":"Mistral NeMo","type":"chat"},{"id":"mistralai/ministral-8b-2512","name":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.41262,"output":0.41262,"cache_read":0.020631},"canonical_model_id":"mistral/ministral-8b-2512","display_name":"Ministral 3 8B 2512","type":"chat"},{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.06877,"output":0.110032},"canonical_model_id":"mistral/mistral-small-24b-instruct-2501","display_name":"Small 3","type":"chat"},{"id":"mistralai/devstral-2512","name":"Devstral 2 2512","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.605176,"output":3.02588,"cache_read":0.060518},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2 2512","type":"chat"},{"id":"mistralai/mistral-saba","name":"Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":26214},"cost":{"input":0.27508,"output":0.82524,"cache_read":0.027508},"canonical_model_id":"mistral/mistral-saba","display_name":"Saba","type":"chat"},{"id":"mistralai/mistral-medium-3-5","name":"Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":209715},"cost":{"input":2.0631,"output":10.3155},"canonical_model_id":"mistral/mistral-medium-3-5","display_name":"Medium 3.5","type":"chat"},{"id":"mistralai/mistral-medium-3.1","name":"Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":104857},"cost":{"input":0.55016,"output":2.7508,"cache_read":0.055016},"canonical_model_id":"mistral/mistral-medium-3.1","display_name":"Medium 3.1","type":"chat"},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.103155,"output":0.27508},"canonical_model_id":"mistral/mistral-small-3.2-24b-instruct","display_name":"Small 3.2 24B","type":"chat"},{"id":"mistralai/mistral-large","name":"Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11-30","release_date":"2024-02-26","last_updated":"2024-02-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":102400},"cost":{"input":2.7508,"output":8.2524,"cache_read":0.27508},"canonical_model_id":"mistral/mistral-large","display_name":"Large","type":"chat"},{"id":"mistralai/mistral-small-2603","name":"Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.257888,"output":1.03155,"cache_read":0.020631},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Small 4","type":"chat"},{"id":"mistralai/mistral-medium-3","name":"Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":104857},"cost":{"input":0.55016,"output":2.7508,"cache_read":0.055016},"canonical_model_id":"mistral/mistral-medium-3","display_name":"Medium 3","type":"chat"},{"id":"mistralai/voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32768},"cost":{"input":0.13754,"output":0.41262,"cache_read":0.013754},"canonical_model_id":"mistral/voxtral-small-24b-2507","display_name":"Voxtral Small 24B 2507","type":"chat"},{"id":"mistralai/mistral-large-2407","name":"Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-03-31","release_date":"2024-11-19","last_updated":"2024-11-19","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":104857},"cost":{"input":2.7508,"output":8.2524,"cache_read":0.27508},"canonical_model_id":"mistral/mistral-large-2407","display_name":"Large 2407","type":"chat"},{"id":"mistralai/ministral-14b-2512","name":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.48139,"output":0.48139,"cache_read":0.027508},"canonical_model_id":"mistral/ministral-14b-2512","display_name":"Ministral 3 14B 2512","type":"chat"},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.482765,"output":0.763347},"canonical_model_id":"mistral/mistral-small-3.1-24b-instruct","display_name":"Small 3.1 24B","type":"chat"},{"id":"mistralai/ministral-3b-2512","name":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":104857},"cost":{"input":0.20631,"output":0.20631,"cache_read":0.013754},"canonical_model_id":"mistral/ministral-3b-2512","display_name":"Ministral 3 3B 2512","type":"chat"},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-01-31","release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":52428},"cost":{"input":2.7508,"output":8.2524,"cache_read":0.27508},"canonical_model_id":"mistral/mixtral-8x22b-instruct","display_name":"Mixtral 8x22B Instruct","type":"chat"},{"id":"mistralai/codestral-2508","name":"Codestral 2508","description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"cost":{"input":0.41262,"output":1.23786,"cache_read":0.041262},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 2508","type":"chat"},{"id":"sakana/fugu-max","name":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.7508,"output":8.2524,"cache_read":0.34385},"canonical_model_id":"sakana/fugu-max","display_name":"Fugu Max","type":"chat"},{"id":"sakana/fugu-ultra-v2","name":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-08-28","release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6.877,"output":41.262,"cache_read":0.6877},"canonical_model_id":"sakana/fugu-ultra-v2","display_name":"Fugu Ultra v2","type":"chat"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6.877,"output":41.262,"cache_read":0.6877},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.82524,"output":3.4385,"cache_read":0.20631},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":1.3754,"output":4.1262},"canonical_model_id":"moonshotai/kimi-k2-0905","display_name":"Kimi K2 0905","type":"chat"},{"id":"moonshotai/kimi-k2","name":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12-31","release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.783978,"output":3.16342},"canonical_model_id":"moonshotai/kimi-k2","display_name":"Kimi K2 0711","type":"chat"},{"id":"rekaai/reka-edge","name":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.13754,"output":0.13754},"canonical_model_id":"rekaai/reka-edge","display_name":"Reka Edge","type":"chat"},{"id":"xiaomi/mimo-v2.5","name":"MiMo V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.192556,"output":0.385112,"cache_read":0.003851},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.598299,"output":1.196598,"cache_read":0.004951},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-06-30","release_date":"2023-07-22","last_updated":"2023-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":6144,"output":4096},"cost":{"input":0.6877,"output":1.03155},"canonical_model_id":"undi95/remm-slerp-l2-13b","display_name":"ReMM SLERP 13B","type":"chat"},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","description":"Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2023-08-10","last_updated":"2023-08-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":2.578875,"output":2.578875,"cache_read":2.578875},"canonical_model_id":"gryphe/mythomax-l2-13b","display_name":"MythoMax 13B","type":"chat"},{"id":"mancer/weaver","name":"Weaver (alpha)","description":"General-purpose chat model for instruction following, writing, and analysis","family":"alpha","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-06-30","release_date":"2023-08-02","last_updated":"2023-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":2000},"cost":{"input":1.03155,"output":1.3754},"canonical_model_id":"mancer/weaver","display_name":"Weaver (alpha)","type":"chat"},{"id":"stepfun/step-5-preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":1.3754,"output":3.71358,"cache_read":0.06877},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"inception/mercury-2.5","name":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":260000,"output":65536},"cost":{"input":0.27508,"output":1.03155,"cache_read":0.027508},"canonical_model_id":"inception/mercury-2.5","display_name":"Mercury 2.5","type":"chat"},{"id":"inception/mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.34385,"output":1.03155,"cache_read":0.034385},"canonical_model_id":"inception/mercury-2","display_name":"Mercury 2","type":"chat"},{"id":"amazon/nova-lite-v1","name":"Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":0.082524,"output":0.330096},"canonical_model_id":"amazon/nova-lite-v1","display_name":"Nova Lite 1.0","type":"chat"},{"id":"amazon/nova-pro-v1","name":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":1.10032,"output":4.40128},"canonical_model_id":"amazon/nova-pro-v1","display_name":"Nova Pro 1.0","type":"chat"},{"id":"amazon/nova-micro-v1","name":"Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":5120},"cost":{"input":0.048139,"output":0.192556},"canonical_model_id":"amazon/nova-micro-v1","display_name":"Nova Micro 1.0","type":"chat"},{"id":"relace/relace-search","name":"Search","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":1.3754,"output":4.1262},"canonical_model_id":"relace/relace-search","display_name":"Search","type":"chat"},{"id":"relace/relace-apply-3","name":"Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":1.16909,"output":1.71925},"canonical_model_id":"relace/relace-apply-3","display_name":"Apply 3","type":"chat"},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12-31","release_date":"2025-02-04","last_updated":"2025-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":1.10032,"output":2.20064},"canonical_model_id":"aion-labs/aion-rp-llama-3.1-8b","display_name":"Aion-RP 1.0 (8B)","type":"chat"},{"id":"morph/morph-v3-large","name":"V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":1.23786,"output":2.61326},"canonical_model_id":"morph/morph-v3-large","display_name":"V3 Large","type":"chat"},{"id":"morph/morph-v3-fast","name":"V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":81920,"output":38000},"cost":{"input":1.10032,"output":1.65048},"canonical_model_id":"morph/morph-v3-fast","display_name":"V3 Fast","type":"chat"},{"id":"openai/gpt-5.4-image-2","name":"GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["image","text","pdf"],"output":["image","text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":11.0032,"output":20.631,"cache_read":2.7508},"canonical_model_id":"openai/gpt-5.4-image-2","display_name":"GPT-5.4 Image 2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":41.262,"output":247.572},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":4096},"cost":{"input":0.65,"output":1.95},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5 Turbo","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":41.262,"output":247.572},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.27508,"output":1.71925,"cache_read":0.027508},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":6.5,"output":19.5},"canonical_model_id":"openai/gpt-4o-2024-05-13","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":3.25,"output":13,"cache_read":1.625},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5.6-sol-pro","name":"GPT-5.6 Sol Pro","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5.5016,"output":27.508,"cache_read":0.55016},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.325,"output":2.6,"cache_read":0.0325},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":28.8834,"output":231.0672},"canonical_model_id":"openai/gpt-5.2-pro","display_name":"GPT-5.2 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/o3-mini","name":"o3 Mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.43,"output":5.72,"cache_read":0.715},"canonical_model_id":"openai/o3-mini","display_name":"o3 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":8192},"cost":{"input":39,"output":78,"cache_read":39},"canonical_model_id":"openai/gpt-4","display_name":"GPT-4","type":"chat"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":4.8139,"output":38.5112,"cache_read":0.48139},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 Nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.13,"output":0.52,"cache_read":0.0325},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 Nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.065,"output":0.52,"cache_read":0.0065},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":100000},"cost":{"input":19.5,"output":78,"cache_read":9.75},"canonical_model_id":"openai/o1","display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":20.631,"output":165.048},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.13},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":3.25,"output":13,"cache_read":1.625},"canonical_model_id":"openai/gpt-4o-2024-08-06","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":13,"output":65,"cache_read":1.3},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.6-luna-pro","name":"GPT-5.6 Luna Pro","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.27508,"output":1.65048,"cache_read":0.027508},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o Mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.195,"output":0.78,"cache_read":0.0975},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o Mini","type":"chat"},{"id":"openai/o3-pro","name":"o3 Pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":27.508,"output":110.032},"canonical_model_id":"openai/o3-pro","display_name":"o3 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":117964},"cost":{"input":0.103155,"output":0.41262,"cache_read":0.051578},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.103155,"output":0.41262,"cache_read":0.051578},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"gpt-oss-safeguard-20b","type":"chat"},{"id":"openai/gpt-5-4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":3.25,"output":19.5,"cache_read":0.325},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2.0631,"output":12.3786,"cache_read":0.20631},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.26,"output":1.56,"cache_read":0.026},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1-Codex-Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":3.4385,"output":27.508,"cache_read":0.34385},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT-5.1-Codex-Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2.6,"output":10.4,"cache_read":0.65},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-5-5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":6.5,"output":39,"cache_read":0.65},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":3.25,"output":13,"cache_read":1.625},"canonical_model_id":"openai/gpt-4o-2024-11-20","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 Mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.52,"output":2.08,"cache_read":0.13},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 Mini","type":"chat"},{"id":"openai/gpt-5.6-terra-pro","name":"GPT-5.6 Terra Pro","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.7508,"output":16.5048,"cache_read":0.27508},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.13,"output":0.65,"cache_read":0.013},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5-2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2.275,"output":18.2,"cache_read":0.2275},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.6,"output":15.6,"cache_read":0.26},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":13,"output":39},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/gpt-5-1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.625,"output":13,"cache_read":0.1625},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":117964},"cost":{"input":0.48139,"output":1.30663,"cache_read":0.48139},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.625,"output":13,"cache_read":0.1625},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5.2,"output":26,"cache_read":0.52},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.26},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":206.31,"output":825.24},"canonical_model_id":"openai/o1-pro","display_name":"o1-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"zhipu/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.82,"output":5.72,"cache_read":0.338},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zhipu/glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":131072},"cost":{"input":1.82,"output":5.72,"cache_read":0.338},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3.9,"output":19.5,"cache_read":0.39},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"upstage":{"id":"upstage","api":"https://api.upstage.ai/v1/solar","name":"Upstage","doc":"https://developers.upstage.ai/docs/apis/chat","display_name":"Upstage","models":[{"id":"solar-pro4","name":"Solar Pro 4","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"Solar Pro 4","type":"chat"},{"id":"solar-pro3","name":"solar-pro3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.25,"output":0.25},"display_name":"solar-pro3","type":"chat"},{"id":"solar-mini","name":"solar-mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"solar-mini","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-06-12","last_updated":"2025-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.15,"output":0.15},"display_name":"solar-mini","type":"chat"},{"id":"solar-pro2","name":"solar-pro2","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0.25,"output":0.25},"display_name":"solar-pro2","type":"chat"}]},"vultr":{"id":"vultr","api":"https://api.vultrinference.com/v1","name":"Vultr","doc":"https://api.vultrinference.com/","display_name":"Vultr","models":[{"id":"mimo-v2.6-pro-rl","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.4,"output":0.8},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":1},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.35},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.1,"output":0.25},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.25,"output":1},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat"},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.09,"output":0.18},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.x-menthol","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.4,"output":1.75},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat"},{"id":"nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.25},"canonical_model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","display_name":"Nemotron 3 Nano Omni 30B A3B Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2.6-flash-rl","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.25},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":512000},"cost":{"input":0.2,"output":0.9},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-flash-next","name":"Qwen3.8 Flash Next","description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.1,"output":0.2},"canonical_model_id":"alibaba/qwen3.8-flash-next","display_name":"Qwen3.8 Flash Next","type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.75,"output":3},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.05,"output":0.15},"canonical_model_id":"nvidia/nemotron-3.5-content-safety","display_name":"Nemotron 3.5 Content Safety","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.75,"output":3},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"huggingface":{"id":"huggingface","api":"https://router.huggingface.co/v1","name":"Hugging Face","doc":"https://huggingface.co/docs/inference-providers","display_name":"Hugging Face","models":[{"id":"tencent/Hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":128000},"cost":{"input":0.14,"output":0.58},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/Hy4-preview","name":"Hy4 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.834,"output":2.501},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta-llama/Llama-3.1-8B-Instruct","name":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.06,"output":0.06},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama-3.1-8B-Instruct","type":"chat"},{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.59,"output":0.79},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2-Flash","name":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4096},"cost":{"input":0.1,"output":0.3},"display_name":"MiMo-V2-Flash","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":3},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","description":"MiMo model for long-context reasoning, perception, and agentic tasks","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.4,"output":2},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.5,"output":1.2},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat"},{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":4.05},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.08,"output":0.16},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT","type":"chat"},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.15},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT","type":"chat"},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.1},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B IT","type":"chat"},{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.4},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":1.5},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.4,"output":3},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-11","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":0.25,"output":1},"display_name":"Qwen3-Next-80B-A3B-Instruct","type":"chat"},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen2.5-Coder-32B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.06,"output":0.2},"canonical_model_id":"alibaba/qwen2.5-coder-32b-instruct","display_name":"Qwen2.5-Coder-32B-Instruct","type":"chat"},{"id":"Qwen/Qwen3-Coder-Next","name":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.2,"output":1.5},"display_name":"Qwen3-Coder-Next","type":"chat"},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.7},"canonical_model_id":"alibaba/qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","type":"chat"},{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.98,"output":3.95},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-thinking","display_name":"Qwen3 VL 235B A22B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next-80B-A3B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-11","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.3,"output":2},"display_name":"Qwen3-Next-80B-A3B-Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.15,"output":0.95},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.3,"output":3},"display_name":"Qwen3-235B-A22B-Thinking-2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.855,"output":2.565},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen3-235B-A22B","name":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.2,"output":0.8},"canonical_model_id":"alibaba/qwen3-235b-a22b","display_name":"Qwen3 235B-A22B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.29,"output":0.59},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.07,"output":0.26},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen 3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.01,"output":0},"display_name":"Qwen 3 Embedding 8B","type":"embedding"},{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.17,"output":0.25},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3.6},"display_name":"Qwen3.5-397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Embedding-4B","name":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":2048},"cost":{"input":0.01,"output":0},"display_name":"Qwen 3 Embedding 4B","type":"embedding"},{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":2.5,"output":6.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.5},"canonical_model_id":"alibaba/qwen3-30b-a3b","display_name":"Qwen3 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":2,"output":2},"display_name":"Qwen3-Coder-480B-A35B-Instruct","type":"chat"},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.47,"output":3.19},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.27,"output":1},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek-V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":32768},"cost":{"input":0.7,"output":2.5},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.28,"output":0.4},"display_name":"DeepSeek-V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":3,"output":5},"display_name":"DeepSeek-R1-0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":8192},"cost":{"input":0.4,"output":1.3},"canonical_model_id":"deepseek/deepseek-v3","display_name":"DeepSeek-V3","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.27,"output":1.12},"canonical_model_id":"deepseek/deepseek-v3-0324","display_name":"DeepSeek V3 0324","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","name":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.44,"output":1.32},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"stepfun-ai/Step-3.7-Flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"stepfun-ai/Step-3.5-Flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash","type":"chat"},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":512000},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M1-80k","name":"MiniMax M1 80K","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":80000},"cost":{"input":0.55,"output":2.2},"canonical_model_id":"minimax/minimax-m1-80k","display_name":"MiniMax M1 80K","type":"chat"},{"id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-10","release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMaxAI/MiniMax-M2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax-M2","type":"chat"},{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"Kimi-K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2-Instruct","name":"Kimi-K2-Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-07-14","last_updated":"2025-07-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":1,"output":3},"display_name":"Kimi-K2-Instruct","type":"chat"},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-01","last_updated":"2026-01-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"display_name":"Kimi-K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi-K2-Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"display_name":"Kimi-K2-Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Kimi-K2-Instruct-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":1,"output":3},"display_name":"Kimi-K2-Instruct-0905","type":"chat"},{"id":"zai-org/GLM-4.6V-Flash","name":"GLM-4.6V-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9},"canonical_model_id":"zhipuai/glm-4.6v-flash","display_name":"GLM-4.6V-Flash","type":"chat"},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-03","last_updated":"2026-04-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-4.5-Air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.13,"output":0.85},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5-Air","type":"chat"},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-4.5V","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM-4.5V","type":"chat"},{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/AutoGLM-Phone-9B-Multilingual","name":"AutoGLM Phone 9B Multilingual","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-10","last_updated":"2025-12-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.035,"output":0.138},"canonical_model_id":"zhipuai/autoglm-phone-9b-multilingual","display_name":"AutoGLM Phone 9B Multilingual","type":"chat"},{"id":"zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0,"output":0},"display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.5},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.25,"output":0.69},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"volcengine":{"id":"volcengine","api":"https://ark.cn-beijing.volces.com/api/v3","name":"Volcengine Ark","doc":"https://www.volcengine.com/docs/82379/1330310","display_name":"Volcengine Ark","models":[{"id":"glm-5-3-flash-260828","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.11875,"output":0.41563,"cache_read":0.03414},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-1-6-251015","name":"Seed 1.6","description":"ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks","family":"seed","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.11875,"output":1.18747,"cache_read":0.02375,"tiers":[{"input":0.17812,"output":2.37494,"cache_read":0.02375,"tier":{"type":"context","size":32000}},{"input":0.35624,"output":3.56241,"cache_read":0.02375,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-1-6","display_name":"Seed 1.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-2-0-pro-260215","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.47499,"output":2.37494,"cache_read":0.095,"tiers":[{"input":0.71248,"output":3.56241,"cache_read":0.1425,"tier":{"type":"context","size":32000}},{"input":1.42496,"output":7.12482,"cache_read":0.28499,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-pro","display_name":"Seed 2.0 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-2-0-lite-260428","name":"Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":0.08906,"output":0.53436,"cache_read":0.01781,"tiers":[{"input":0.13359,"output":0.80154,"cache_read":0.02672,"tier":{"type":"context","size":32000}},{"input":0.26718,"output":1.60308,"cache_read":0.05344,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-lite","display_name":"Seed 2.0 Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"doubao-seed-2-1-pro-260628","name":"Seed 2.1 Pro","description":"Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.8906,"output":4.45301,"cache_read":0.17812},"canonical_model_id":"bytedance-seed/seed-2.1-pro","display_name":"Seed 2.1 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"doubao-seed-1-6-vision-250815","name":"Seed 1.6 Vision","description":"ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.11875,"output":1.18747,"cache_read":0.02375,"tiers":[{"input":0.17812,"output":2.37494,"cache_read":0.02375,"tier":{"type":"context","size":32000}},{"input":0.35624,"output":3.56241,"cache_read":0.02375,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-1-6-vision","display_name":"Seed 1.6 Vision","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-2-0-mini-260428","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":0.02969,"output":0.29687,"cache_read":0.00594,"tiers":[{"input":0.05937,"output":0.59374,"cache_read":0.01187,"tier":{"type":"context","size":32000}},{"input":0.11875,"output":1.18747,"cache_read":0.02375,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed 2.0 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"doubao-seed-2-0-code-preview-260215","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.47499,"output":2.37494,"cache_read":0.095,"tiers":[{"input":0.71248,"output":3.56241,"cache_read":0.1425,"tier":{"type":"context","size":32000}},{"input":1.42496,"output":7.12482,"cache_read":0.28499,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-2-1-turbo-260628","name":"Seed 2.1 Turbo","description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.4453,"output":2.22651,"cache_read":0.08906},"canonical_model_id":"bytedance-seed/seed-2.1-turbo","display_name":"Seed 2.1 Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5-2-260617","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.18747,"output":4.15615,"cache_read":0.29687},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-1-8-251228","name":"Seed 1.8","description":"ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-28","last_updated":"2025-12-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.11875,"output":1.18747,"cache_read":0.02375,"tiers":[{"input":0.17812,"output":2.37494,"cache_read":0.02375,"tier":{"type":"context","size":32000}},{"input":0.35624,"output":3.56241,"cache_read":0.02375,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-1-8","display_name":"Seed 1.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-evolving","name":"Seed Evolving","description":"Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.8906,"output":4.45301,"cache_read":0.17812},"canonical_model_id":"bytedance-seed/seed-evolving","display_name":"Seed Evolving","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-1-6-flash-250828","name":"Seed 1.6 Flash","description":"Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.02227,"output":0.22265,"cache_read":0.00445,"tiers":[{"input":0.04453,"output":0.4453,"cache_read":0.00445,"tier":{"type":"context","size":32000}},{"input":0.08906,"output":0.8906,"cache_read":0.00445,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"bytedance-seed/seed-1-6-flash","display_name":"Seed 1.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-character-260628","name":"Seed Character","description":"ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.11875,"output":0.29687,"cache_read":0.02375,"tiers":[{"input":0.17812,"output":0.8906,"cache_read":0.02375,"tier":{"type":"context","size":32000}}]},"canonical_model_id":"bytedance-seed/seed-character","display_name":"Seed Character","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro-ga-260813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.3359,"output":4.00771,"cache_read":0.04453},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-flash-ga-260731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.4453,"output":1.3359,"cache_read":0.01484},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"impossibl":{"id":"impossibl","api":"https://api.impossibl.com/v1","name":"Impossibl","doc":"https://impossibl.com/docs/models","display_name":"Impossibl","models":[{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.35,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5-Air","type":"chat"},{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.19,"output":0.51,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":1.87,"output":4.68,"cache_read":0.374},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.3,"cache_read":0.035},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.003},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max-preview","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.5,"output":7.5},"canonical_model_id":"alibaba/qwen3.8-max-preview","display_name":"Qwen3.8 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.05,"tiers":[{"input":1,"output":4,"cache_read":0.2,"tier":{"type":"context","size":262144}}],"context_over_200k":{"input":1,"output":4,"cache_read":0.2}},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.24,"tier":{"type":"context","size":262144}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.24}},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":3,"tiers":[{"input":60,"output":270,"cache_read":3,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270,"cache_read":3}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5-turbo","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":3,"tiers":[{"input":60,"output":270,"cache_read":3,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270,"cache_read":3}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5-codex","display_name":"GPT-5-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"canonical_model_id":"openai/o1","display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"xpersona":{"id":"xpersona","api":"https://www.xpersona.co/v1","name":"Xpersona","doc":"https://www.xpersona.co/docs","display_name":"Xpersona","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0.75,"output":6,"reasoning":6,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":3.7,"reasoning":3.7,"cache_read":0.06},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"xpersona-frieren-coder","name":"Xpersona Frieren 1","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-30","release_date":"2026-05-01","last_updated":"2026-05-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":384000},"cost":{"input":1.5,"output":6,"reasoning":6,"cache_read":0.15},"display_name":"Xpersona Frieren 1","type":"chat"},{"id":"gpt-5.6","name":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":372000,"output":128000},"cost":{"input":1.5,"output":12,"reasoning":12,"cache_read":0.15},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"xpersona-gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-30","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":18,"reasoning":18,"cache_read":0.3},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.55,"output":12.2,"reasoning":12.2,"cache_read":0.155},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":18.5,"reasoning":18.5,"cache_read":0.3},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":0.375,"output":4,"reasoning":4,"cache_read":0.0375},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":1.5,"output":9.25,"reasoning":9.25,"cache_read":0.15},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":1.5,"output":12,"reasoning":12,"cache_read":0.15},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.9,"output":5.55,"reasoning":5.55,"cache_read":0.09},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":372000,"output":128000},"cost":{"input":1.5,"output":2,"reasoning":2,"cache_read":0.15},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":372000,"output":128000},"cost":{"input":1.5,"output":12,"reasoning":12,"cache_read":0.15},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}}]},"qiniu-ai":{"id":"qiniu-ai","api":"https://api.qnaigc.com/v1","name":"Qiniu","doc":"https://developer.qiniu.com/aitokenapi","display_name":"Qiniu","models":[{"id":"glm-4.5","name":"GLM 4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":98304},"display_name":"GLM 4.5","type":"chat"},{"id":"gemini-3.0-flash-preview","name":"Gemini 3.0 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"display_name":"Gemini 3.0 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"doubao-seed-2.0-mini","name":"Doubao Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"display_name":"Doubao Seed 2.0 Mini","type":"chat"},{"id":"mimo-v2-flash","name":"Mimo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-16","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"canonical_model_id":"xiaomi/mimo-v2-flash","display_name":"Mimo-V2-Flash","type":"chat"},{"id":"doubao-seed-2.0-lite","name":"Doubao Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"display_name":"Doubao Seed 2.0 Lite","type":"chat"},{"id":"doubao-seed-1.6-thinking","name":"Doubao-Seed 1.6 Thinking","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"display_name":"Doubao-Seed 1.6 Thinking","type":"chat"},{"id":"gemini-2.5-flash-image","name":"Gemini 2.5 Flash Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-22","last_updated":"2025-10-22","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":32768,"output":8192},"display_name":"Gemini 2.5 Flash Image","type":"image-generation"},{"id":"gemini-3.0-pro-image-preview","name":"Gemini 3.0 Pro Image Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":8192},"display_name":"Gemini 3.0 Pro Image Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-3.5-haiku","name":"Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"display_name":"Claude 3.5 Haiku","type":"chat"},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235b A22B Instruct 2507","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":64000},"display_name":"Qwen3 235b A22B Instruct 2507","type":"chat"},{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-12","last_updated":"2025-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"display_name":"Qwen3 Next 80B A3B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-max-2025-01-25","name":"Qwen2.5-Max-2025-01-25","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"display_name":"Qwen2.5-Max-2025-01-25","type":"chat"},{"id":"deepseek-v3-0324","name":"DeepSeek-V3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"display_name":"DeepSeek-V3-0324","type":"chat"},{"id":"qwen3-32b","name":"Qwen3 32B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40000,"output":4096},"display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-max","name":"Qwen3 Max","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-4.5-sonnet","name":"Claude 4.5 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"display_name":"Claude 4.5 Sonnet","type":"chat"},{"id":"deepseek-v3","name":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"display_name":"DeepSeek-V3","type":"chat"},{"id":"qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-14","last_updated":"2025-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":4096},"display_name":"Qwen3 Coder 480B A35B Instruct","type":"chat"},{"id":"qwen-turbo","name":"Qwen-Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":4096},"display_name":"Qwen-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.0-flash","name":"Gemini 2.0 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":8192},"display_name":"Gemini 2.0 Flash","type":"chat"},{"id":"gemini-2.0-flash-lite","name":"Gemini 2.0 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":8192},"display_name":"Gemini 2.0 Flash Lite","type":"chat"},{"id":"claude-4.0-sonnet","name":"Claude 4.0 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"display_name":"Claude 4.0 Sonnet","type":"chat"},{"id":"qwen2.5-vl-7b-instruct","name":"Qwen 2.5 VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"Qwen 2.5 VL 7B Instruct","type":"chat"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":4096},"display_name":"Qwen3 235B A22B Thinking 2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-235b-a22b","name":"Qwen 3 235B A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"Qwen 3 235B A22B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-2.0-pro","name":"Doubao Seed 2.0 Pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"display_name":"Doubao Seed 2.0 Pro","type":"chat"},{"id":"doubao-seed-1.6-flash","name":"Doubao-Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"display_name":"Doubao-Seed 1.6 Flash","type":"chat"},{"id":"qwen3-max-preview","name":"Qwen3 Max Preview","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-06","last_updated":"2025-09-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"display_name":"Qwen3 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-12","last_updated":"2025-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"display_name":"Qwen3 Next 80B A3B Instruct","type":"chat"},{"id":"qwen3-vl-30b-a3b-thinking","name":"Qwen3-Vl 30b A3b Thinking","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-09","last_updated":"2026-02-09","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"Qwen3-Vl 30b A3b Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-1.5-pro-32k","name":"Doubao 1.5 Pro 32k","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":12000},"display_name":"Doubao 1.5 Pro 32k","type":"chat"},{"id":"claude-3.5-sonnet","name":"Claude 3.5 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-09","last_updated":"2025-09-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8200},"display_name":"Claude 3.5 Sonnet","type":"chat"},{"id":"gpt-oss-20b","name":"gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"display_name":"gpt-oss-20b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":64000},"display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen-vl-max-2025-01-25","name":"Qwen VL-MAX-2025-01-25","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"display_name":"Qwen VL-MAX-2025-01-25","type":"chat"},{"id":"doubao-1.5-thinking-pro","name":"Doubao 1.5 Thinking Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"display_name":"Doubao 1.5 Thinking Pro","type":"chat"},{"id":"claude-4.5-haiku","name":"Claude 4.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"display_name":"Claude 4.5 Haiku","type":"chat"},{"id":"kling-v2-6","name":"Kling-V2 6","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-13","last_updated":"2026-01-13","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":false,"limit":{"context":99999999,"output":99999999},"display_name":"Kling-V2 6","type":"chat"},{"id":"claude-4.1-opus","name":"Claude 4.1 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"display_name":"Claude 4.1 Opus","type":"chat"},{"id":"claude-3.7-sonnet","name":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"display_name":"Claude 3.7 Sonnet","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"MiniMax-M1","name":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":80000},"display_name":"MiniMax M1","type":"chat"},{"id":"doubao-seed-1.6","name":"Doubao-Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"display_name":"Doubao-Seed 1.6","type":"chat"},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40000,"output":4096},"display_name":"Qwen3 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-22","last_updated":"2026-02-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"display_name":"Qwen3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-2.0-code","name":"Doubao Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"display_name":"Doubao Seed 2.0 Code","type":"chat"},{"id":"claude-4.0-opus","name":"Claude 4.0 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"display_name":"Claude 4.0 Opus","type":"chat"},{"id":"kimi-k2","name":"Kimi K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"display_name":"Kimi K2","type":"chat"},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen3 30b A3b Instruct 2507","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"Qwen3 30b A3b Instruct 2507","type":"chat"},{"id":"qwen2.5-vl-72b-instruct","name":"Qwen 2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"Qwen 2.5 VL 72B Instruct","type":"chat"},{"id":"doubao-1.5-vision-pro","name":"Doubao 1.5 Vision Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"display_name":"Doubao 1.5 Vision Pro","type":"chat"},{"id":"claude-4.5-opus","name":"Claude 4.5 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"display_name":"Claude 4.5 Opus","type":"chat"},{"id":"deepseek-v3.1","name":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"DeepSeek-V3.1","type":"chat"},{"id":"deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30b A3b Thinking 2507","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":126000,"output":32000},"display_name":"Qwen3 30b A3b Thinking 2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":{"supported":true,"default":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":64000},"display_name":"Gemini 2.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"deepseek-r1-0528","name":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"DeepSeek-R1-0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.5-air","name":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":4096},"display_name":"GLM 4.5 Air","type":"chat"},{"id":"gpt-oss-120b","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"display_name":"gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.0-pro-preview","name":"Gemini 3.0 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"display_name":"Gemini 3.0 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"deepseek/deepseek-v3.2-exp-thinking","name":"DeepSeek/DeepSeek-V3.2-Exp-Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"DeepSeek/DeepSeek-V3.2-Exp-Thinking","type":"chat"},{"id":"deepseek/deepseek-math-v2","name":"Deepseek/Deepseek-Math-V2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-04","last_updated":"2025-12-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":160000,"output":160000},"display_name":"Deepseek/Deepseek-Math-V2","type":"chat"},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"DeepSeek/DeepSeek-V3.1-Terminus","type":"chat"},{"id":"deepseek/deepseek-v3.2-251201","name":"Deepseek/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"Deepseek/DeepSeek-V3.2","type":"chat"},{"id":"deepseek/deepseek-v3.1-terminus-thinking","name":"DeepSeek/DeepSeek-V3.1-Terminus-Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"DeepSeek/DeepSeek-V3.1-Terminus-Thinking","type":"chat"},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"display_name":"DeepSeek/DeepSeek-V3.2-Exp","type":"chat"},{"id":"z-ai/glm-4.6","name":"Z-AI/GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-10-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"display_name":"Z-AI/GLM 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5","name":"Z-Ai/GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"display_name":"Z-Ai/GLM 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-4.7","name":"Z-Ai/GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"display_name":"Z-Ai/GLM 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/autoglm-phone-9b","name":"Z-Ai/Autoglm Phone 9b","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":12800,"output":4096},"display_name":"Z-Ai/Autoglm Phone 9b","type":"chat"},{"id":"meituan/longcat-flash-chat","name":"Meituan/Longcat-Flash-Chat","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-11-05","last_updated":"2025-11-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"display_name":"Meituan/Longcat-Flash-Chat","type":"chat"},{"id":"meituan/longcat-flash-lite","name":"Meituan/Longcat-Flash-Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":320000},"display_name":"Meituan/Longcat-Flash-Lite","type":"chat"},{"id":"x-ai/grok-4-fast-reasoning","name":"X-Ai/Grok-4-Fast-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"display_name":"X-Ai/Grok-4-Fast-Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.1-fast-reasoning","name":"X-Ai/Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":20000000,"output":2000000},"display_name":"X-Ai/Grok 4.1 Fast Reasoning","type":"chat"},{"id":"x-ai/grok-4-fast-non-reasoning","name":"X-Ai/Grok-4-Fast-Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"display_name":"X-Ai/Grok-4-Fast-Non-Reasoning","type":"chat"},{"id":"x-ai/grok-code-fast-1","name":"x-AI/Grok-Code-Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":10000},"display_name":"x-AI/Grok-Code-Fast 1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.1-fast","name":"x-AI/Grok-4.1-Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"display_name":"x-AI/Grok-4.1-Fast","type":"chat"},{"id":"x-ai/grok-4.1-fast-non-reasoning","name":"X-Ai/Grok 4.1 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"display_name":"X-Ai/Grok 4.1 Fast Non Reasoning","type":"chat"},{"id":"x-ai/grok-4-fast","name":"x-AI/Grok-4-Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-20","last_updated":"2025-09-20","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"display_name":"x-AI/Grok-4-Fast","type":"chat"},{"id":"stepfun-ai/gelab-zero-4b-preview","name":"Stepfun-Ai/Gelab Zero 4b Preview","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"display_name":"Stepfun-Ai/Gelab Zero 4b Preview","type":"chat"},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-07","last_updated":"2025-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":100000},"display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.5","name":"Moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"display_name":"Moonshotai/Kimi-K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":100000},"display_name":"Kimi K2 0905","type":"chat"},{"id":"xiaomi/mimo-v2-flash","name":"Xiaomi/Mimo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-16","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"canonical_model_id":"xiaomi/mimo-v2-flash","display_name":"Xiaomi/Mimo-V2-Flash","type":"chat"},{"id":"minimax/minimax-m2.5","name":"Minimax/Minimax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":128000},"display_name":"Minimax/Minimax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5-highspeed","name":"Minimax/Minimax-M2.5 Highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":128000},"display_name":"Minimax/Minimax-M2.5 Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1","name":"Minimax/Minimax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":128000},"display_name":"Minimax/Minimax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2","name":"Minimax/Minimax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"display_name":"Minimax/Minimax-M2","type":"chat"},{"id":"stepfun/step-3.5-flash","name":"Stepfun/Step-3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-02","last_updated":"2026-02-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":64000,"output":4096},"display_name":"Stepfun/Step-3.5 Flash","type":"chat"},{"id":"openai/gpt-5.2","name":"OpenAI/GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"display_name":"OpenAI/GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"OpenAI/GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-19","last_updated":"2025-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"display_name":"OpenAI/GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"modelscope":{"id":"modelscope","api":"https://api-inference.modelscope.cn/v1","name":"ModelScope","doc":"https://modelscope.cn/docs/model-service/API-Inference/intro","display_name":"ModelScope","models":[{"id":"ZhipuAI/GLM-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":98304},"cost":{"input":0,"output":0},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ZhipuAI/GLM-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0},"display_name":"GLM-4.5","type":"chat"},{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"display_name":"Qwen3 30B A3B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0},"display_name":"Qwen3-235B-A22B-Thinking-2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0},"display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen3-30B-A3B-Thinking-2507","name":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"display_name":"Qwen3 30B A3B Thinking 2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"display_name":"Qwen3 Coder 30B A3B Instruct","type":"chat"}]},"google":{"id":"google","name":"google","doc":"https://ai.google.dev/gemini-api/docs/models","display_name":"google","models":[{"id":"gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"display_name":"Gemini Flash Latest","type":"chat"},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"display_name":"Gemma 4 31B IT","type":"chat"},{"id":"gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":1.5,"output":17.5},"canonical_model_id":"google/gemini-omni-flash-preview","display_name":"Gemini Omni Flash Preview","type":"chat"},{"id":"gemini-3.1-flash-image-preview","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":60},"display_name":"Nano Banana 2","extra_capabilities":{"reasoning":{"supported":true}},"type":"image-generation"},{"id":"veo-3.1-lite-generate-preview","name":"Veo 3.1 lite","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"canonical_model_id":"google/veo-3.1-lite-generate-preview","display_name":"Veo 3.1 lite","type":"chat"},{"id":"lyria-3-pro-preview","name":"Lyria 3 Pro Preview","description":"Music generation model for full-length songs from text or images with vocals and structure","family":"lyria","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/lyria-3-pro-preview","display_name":"Lyria 3 Pro Preview","type":"chat"},{"id":"gemini-3.1-flash-tts-preview","name":"Gemini 3.1 Flash TTS Preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","family":"gemini-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":1,"output":20},"canonical_model_id":"google/gemini-3.1-flash-tts-preview","display_name":"Gemini 3.1 Flash TTS Preview","type":"chat"},{"id":"gemini-2.5-flash-image","name":"Gemini 2.5 Flash Image","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":false,"reasoning":{"supported":false},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30,"cache_read":0.075},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Gemini 2.5 Flash Image","type":"image-generation"},{"id":"gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"display_name":"Gemini Flash-Lite Latest","type":"chat"},{"id":"gemini-embedding-2","name":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","family":"gemini","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1},"cost":{"input":0.2,"output":0,"input_audio":6.5},"canonical_model_id":"google/gemini-embedding-2","display_name":"Gemini Embedding 2","type":"embedding"},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"gemini-3-pro-image-preview","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":2,"output":120},"canonical_model_id":"google/gemini-3-pro-image-preview","display_name":"Nano Banana Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"image-generation"},{"id":"gemini-2.5-pro-preview-tts","name":"Gemini 2.5 Pro Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-05-01","last_updated":"2025-05-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":1,"output":20},"display_name":"Gemini 2.5 Pro Preview TTS","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":60},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","extra_capabilities":{"reasoning":{"supported":true}},"type":"image-generation"},{"id":"lyria-3-clip-preview","name":"Lyria 3 Clip Preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","family":"lyria","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/lyria-3-clip-preview","display_name":"Lyria 3 Clip Preview","type":"chat"},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"display_name":"Gemini 3.1 Pro Preview","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-2.5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview 10-2025","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-07","last_updated":"2025-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":1.25,"output":10,"tiers":[{"input":2.5,"output":15,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15}},"canonical_model_id":"google/gemini-2.5-computer-use-preview-10-2025","display_name":"Gemini 2.5 Computer Use Preview 10-2025","type":"chat"},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"display_name":"Gemini 3.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true,"budget":{"min":128,"max":32768,"default":-1}},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"search":{"supported":true,"default":false},"type":"chat"},{"id":"gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":120},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"image-generation"},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":24576,"default":-1}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"search":{"supported":true,"default":false},"type":"chat"},{"id":"gemini-2.5-flash-preview-tts","name":"Gemini 2.5 Flash Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-05-01","last_updated":"2025-05-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":0.5,"output":10},"display_name":"Gemini 2.5 Flash Preview TTS","type":"chat"},{"id":"gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":30},"canonical_model_id":"google/gemini-3.1-flash-lite-image","display_name":"Nano Banana 2 Lite","extra_capabilities":{"reasoning":{"supported":true}},"type":"image-generation"},{"id":"deep-research-preview-04-2026","name":"Deep Research Preview (Apr-21-2026)","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/deep-research-preview-04-2026","display_name":"Deep Research Preview (Apr-21-2026)","type":"chat"},{"id":"deep-research-max-preview-04-2026","name":"Deep Research Max Preview (Apr-21-2026)","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/deep-research-max-preview-04-2026","display_name":"Deep Research Max Preview (Apr-21-2026)","type":"chat"},{"id":"veo-3.1-fast-generate-preview","name":"Veo 3.1 fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-10-15","last_updated":"2026-01-01","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"canonical_model_id":"google/veo-3.1-fast-generate-preview","display_name":"Veo 3.1 fast","type":"chat"},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"veo-3.1-generate-preview","name":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-10-15","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"status":"beta","canonical_model_id":"google/veo-3.1-generate-preview","display_name":"Veo 3.1","type":"chat"},{"id":"gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"display_name":"Gemini 3.1 Pro Preview Custom Tools","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"display_name":"Gemini 3 Flash Preview","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-3.5-live-translate-preview","name":"Gemini 3.5 Live Translate Preview","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","family":"gemini-pro","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["audio"],"output":["audio","text"]},"open_weights":false,"limit":{"context":16384,"output":32768},"cost":{"input":3.5,"output":21,"input_audio":3.5,"output_audio":21},"canonical_model_id":"google/gemini-3.5-live-translate-preview","display_name":"Gemini 3.5 Live Translate Preview","type":"chat"},{"id":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false,"budget":{"min":512,"max":24576,"default":-1}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"display_name":"Gemini 2.5 Flash Lite","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"search":{"supported":true,"default":false},"type":"chat"},{"id":"gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":1},"cost":{"input":0.15,"output":0},"display_name":"Gemini Embedding 001","type":"embedding"},{"id":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Legacy model retained for compatibility with older integrations","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"gemini-3.1-flash-live-preview","name":"Gemini 3.1 Flash Live Preview","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-26","last_updated":"2026-03-26","modalities":{"input":["text","image","video","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.75,"output":4.5,"input_audio":3,"output_audio":12},"canonical_model_id":"google/gemini-3.1-flash-live-preview","display_name":"Gemini 3.1 Flash Live Preview","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":2,"output":10,"cache_read":0.1,"input_audio":2},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","metadata":{"pricingBasis":"standard-introductory","pricingValidUntil":"2026-11-30","notes":["Google ignores temperature, top_p, and top_k for this model.","Introductory pricing through November 30, 2026 is $2 input / $10 output with $0.10 cached input per million tokens; from December 1, 2026 it is $4 input / $20 output with $0.20 cached input."]},"type":"chat"},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"display_name":"Gemini 3.1 Flash Lite","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"gemini-2.5-flash-preview-09-2025","name":"Gemini 2.5 Flash Preview 09 2025","display_name":"Gemini 2.5 Flash Preview 09 2025","temperature":true,"attachment":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":65536},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":24576,"default":-1}},"search":{"supported":true,"default":false},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-2.5-flash-image-preview","name":"Gemini 2.5 Flash Image Preview","display_name":"Gemini 2.5 Flash Image Preview","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text","image"],"output":["text","image"]},"limit":{"context":32768,"output":32768},"reasoning":{"supported":false},"type":"image-generation"},{"id":"gemini-2.5-flash-lite-preview-09-2025","name":"Gemini 2.5 Flash Lite Preview 09 2025","display_name":"Gemini 2.5 Flash Lite Preview 09 2025","temperature":true,"attachment":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":65536},"reasoning":{"supported":true,"default":false,"budget":{"min":512,"max":24576,"default":-1}},"search":{"supported":true,"default":false},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"gemini-2.0-flash","name":"Gemini 2.0 Flash","display_name":"Gemini 2.0 Flash","temperature":true,"attachment":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":8192},"reasoning":{"supported":true,"default":false},"search":{"supported":true,"default":false},"type":"chat"},{"id":"gemini-2.0-flash-preview-image-generation","name":"Gemini 2.0 Flash Preview Image Generation","display_name":"Gemini 2.0 Flash Preview Image Generation","temperature":true,"attachment":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text","image"]},"limit":{"context":32000,"output":8192},"reasoning":{"supported":false},"search":{"supported":false},"type":"chat"},{"id":"gemini-2.0-flash-lite","name":"Gemini 2.0 Flash Lite","display_name":"Gemini 2.0 Flash Lite","temperature":true,"attachment":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":8192},"reasoning":{"supported":false},"search":{"supported":false},"type":"chat"}]},"vancine":{"id":"vancine","api":"https://vancine.com/v1","name":"Vancine","doc":"https://vancine.com/docs","display_name":"Vancine","models":[{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.24,"output":0.96,"cache_read":0.048},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.12,"output":0.4,"cache_read":0.024},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.6,"output":4.8,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2.4,"output":12,"cache_read":0.24},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.24,"output":0.96,"cache_read":0.0048},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.12,"output":0.38,"cache_read":0.013},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":64000},"cost":{"input":0.67,"output":2,"cache_read":0.034},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.12,"output":3.52,"cache_read":0.208},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"zhipuai-coding-plan":{"id":"zhipuai-coding-plan","api":"https://open.bigmodel.cn/api/coding/paas/v4","name":"Zhipu AI Coding Plan","doc":"https://docs.bigmodel.cn/cn/coding-plan/overview","display_name":"Zhipu AI Coding Plan","models":[{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3-highspeed","name":"GLM-5.3 Highspeed","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"display_name":"GLM-4.6V","type":"chat"}]},"lucidquery":{"id":"lucidquery","api":"https://api.lucidquery.com/v1","name":"LucidQuery","doc":"https://lucidquery.com/docs","display_name":"LucidQuery","models":[{"id":"lucidquery-agi-01-frontier","name":"AGI-01 Frontier","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-06-05","release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":120000},"cost":{"input":4.5,"output":22},"display_name":"AGI-01 Frontier","type":"chat"},{"id":"lucidquery-nexus-coder","name":"LucidQuery Nexus Coder","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"lucid","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2025-08-01","release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":250000,"output":60000},"cost":{"input":2,"output":5},"display_name":"LucidQuery Nexus Coder","type":"chat"},{"id":"lucidnova-rf1-100b","name":"LucidNova RF1 100B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2025-09-16","release_date":"2024-12-28","last_updated":"2025-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":120000,"output":8000},"cost":{"input":2,"output":5},"display_name":"LucidNova RF1 100B","type":"chat"},{"id":"lucidquery-agi-01-swift","name":"AGI-01 Swift","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-06-05","release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":120000},"cost":{"input":2.5,"output":15},"display_name":"AGI-01 Swift","type":"chat"}]},"gmicloud":{"id":"gmicloud","api":"https://api.gmi-serving.com/v1","name":"GMI Cloud","doc":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","display_name":"GMI Cloud","models":[{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":409600,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":409600,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":409600,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"Qwen/Qwen3.7-Max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen3.8-Flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048575,"output":131072},"cost":{"input":0.16,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":384000},"cost":{"input":0.112,"output":0.224,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.392,"output":2.784,"cache_read":0.116},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.24,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.24}},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.855,"output":3.6,"cache_read":0.144},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2-FP8","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.979,"output":3.08,"cache_read":0.182},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5-FP8","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":1.92,"cache_read":0.12},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.1-FP8","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.98,"output":3.08,"cache_read":0.182},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"oci":{"id":"oci","api":"https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/openai/v1","name":"OCI Generative AI","doc":"https://docs.oracle.com/en-us/iaas/Content/generative-ai/pretrained-models.htm","display_name":"OCI Generative AI","models":[{"id":"xai.grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat"},{"id":"xai.grok-4.20-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"meta.llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.72,"output":0.72},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"meta.llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":192000,"output":16384},"cost":{"input":0.72,"output":0.72},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B Instruct","type":"chat"},{"id":"xai.grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat"},{"id":"meta.llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":16384},"cost":{"input":0.72,"output":0.72},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct","type":"chat"},{"id":"openai.gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai.gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.07,"output":0.3},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xai.grok-4.20-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"}]},"cloudflare-ai-gateway":{"id":"cloudflare-ai-gateway","name":"Cloudflare AI Gateway","doc":"https://developers.cloudflare.com/ai-gateway/","display_name":"Cloudflare AI Gateway","models":[{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"unbiased/pareto","name":"Pareto","description":"Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":2.5,"output":7.5,"cache_read":0.25},"canonical_model_id":"unbiased/pareto","display_name":"Pareto","type":"chat"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.16},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.16},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.16},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-wonder-1.0","name":"Muse Wonder","description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"meta/muse-wonder-1.0","display_name":"Muse Wonder","type":"chat"},{"id":"meta/muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1040000,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"alibaba/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"alibaba/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.2,"output":6},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.32,"output":1.28,"cache_read":0.064},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"reflection-ai/beam-1.0-501b-a23b","name":"Beam 1.0 501B A23B","description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-06-30","release_date":"2026-10-05","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"reflection/beam-1.0-501b-a23b","display_name":"Beam 1.0 501B A23B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks/ember-1","name":"Ember-1","description":"Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1040000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"fireworks/ember-1","display_name":"Ember-1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.25,"output":5,"cache_read":0.625},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":10,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"clarifai":{"id":"clarifai","api":"https://api.clarifai.com/v2/ext/openai/v1","name":"Clarifai","doc":"https://docs.clarifai.com/compute/inference/","display_name":"Clarifai","models":[{"id":"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput","name":"MiniMax-M2.5 High Throughput","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"display_name":"MiniMax-M2.5 High Throughput","type":"chat"},{"id":"clarifai/main/models/mm-poly-8b","name":"MM Poly 8B","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"mm-poly","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-06","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.658,"output":1.11},"display_name":"MM Poly 8B","type":"chat"},{"id":"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","name":"DeepSeek OCR","description":"OCR model for extracting structured text from documents and screenshots","family":"deepseek","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-20","last_updated":"2026-02-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.2,"output":0.7},"display_name":"DeepSeek OCR","type":"chat"},{"id":"mistralai/completion/models/Ministral-3-3B-Reasoning-2512","name":"Ministral 3 3B Reasoning 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12","last_updated":"2026-02-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.039,"output":0.54825},"display_name":"Ministral 3 3B Reasoning 2512","type":"chat"},{"id":"mistralai/completion/models/Ministral-3-14B-Reasoning-2512","name":"Ministral 3 14B Reasoning 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-01","last_updated":"2025-12-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2.5,"output":1.7},"display_name":"Ministral 3 14B Reasoning 2512","type":"chat"},{"id":"moonshotai/chat-completion/models/Kimi-K2_6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"arcee_ai/AFM/models/trinity-mini","name":"Trinity Mini","description":"Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads","family":"trinity","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-01","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.045,"output":0.15},"canonical_model_id":"arcee-ai/trinity-mini","display_name":"Trinity Mini","type":"chat"},{"id":"qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-31","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.11458,"output":0.74812},"display_name":"Qwen3 Coder 30B A3B Instruct","type":"chat"},{"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.5},"display_name":"Qwen3 30B A3B Instruct 2507","type":"chat"},{"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","name":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-31","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.36,"output":1.3},"display_name":"Qwen3 30B A3B Thinking 2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/chat-completion/models/gpt-oss-120b-high-throughput","name":"GPT OSS 120B High Throughput","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.09,"output":0.36},"display_name":"GPT OSS 120B High Throughput","type":"chat"},{"id":"openai/chat-completion/models/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-12-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.045,"output":0.18},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"aiand":{"id":"aiand","api":"https://api.aiand.com/v1","name":"ai&","doc":"https://docs.aiand.com/","display_name":"ai&","models":[{"id":"motif-technologies/motif-3","name":"Motif 3","description":"Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.","family":"motif","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2,"cache_read":0.2},"canonical_model_id":"motif-technologies/motif-3","display_name":"Motif 3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.3,"output":0.6,"cache_read":0.02},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1,"output":2.5,"cache_read":0.25},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.25,"cache_read":0.08},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":12.5,"cache_read":0.5},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.75,"output":3.5,"cache_read":0.2},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048550,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":4,"cache_read":0.3},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":4,"cache_read":0.3},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.4,"output":3,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.32,"output":3.2,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.08},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"frogbot":{"id":"frogbot","api":"https://app.frogbot.ai/api/v1","name":"FrogBot","doc":"https://docs.frogbot.ai","display_name":"FrogBot","models":[{"id":"grok-4-1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast (Reasoning)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-4-mini","name":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast (Non-Reasoning)","type":"chat"},{"id":"gpt-4o","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"display_name":"GPT-4o","type":"chat"},{"id":"minimax-m2-5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-01-15","last_updated":"2025-02-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"display_name":"MiniMax-M2.5","type":"chat"},{"id":"gpt-5-4-nano","name":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"kimi-k2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.6,"output":3,"cache_read":0.1},"display_name":"Kimi-K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.2},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.31},"display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-07-17","last_updated":"2025-07-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.075},"display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"minimax-m2-7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax-M2.7","type":"chat"},{"id":"kimi-k2-6","name":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"Kimi-K2.6","type":"chat"},{"id":"grok-code-fast-1","name":"Grok 4.1 Fast (Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.2,"output":1.5,"cache_read":0.02},"display_name":"Grok 4.1 Fast (Reasoning)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen-3-6-plus","name":"Qwen 3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.1},"display_name":"Qwen 3.6 Plus","type":"chat"},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"grok-4-3","name":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"display_name":"Grok 4.3","type":"chat"},{"id":"gpt-5-5","name":"GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-02-18","last_updated":"2026-02-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2},"display_name":"Gemini 3.1 Pro Preview","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek v4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":1.74,"output":3.48,"cache_read":0.14},"display_name":"DeepSeek v4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-5-3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"zai-glm-5-1","name":"Z.AI GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-01-20","last_updated":"2025-02-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":8192},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"display_name":"Z.AI GLM-5.1","type":"chat"}]},"stackit":{"id":"stackit","api":"https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1","name":"STACKIT","doc":"https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models","display_name":"STACKIT","models":[{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-05-17","last_updated":"2025-05-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":37000,"output":4096},"cost":{"input":0.53,"output":0.76},"display_name":"Gemma 3 27B","type":"chat"},{"id":"intfloat/e5-mistral-7b-instruct","name":"E5 Mistral 7B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0.02,"output":0.02},"display_name":"E5 Mistral 7B","type":"chat"},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","name":"Qwen3-VL 235B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":218000,"output":16384},"cost":{"input":1.76,"output":2.05},"display_name":"Qwen3-VL 235B","type":"chat"},{"id":"Qwen/Qwen3-VL-Embedding-8B","name":"Qwen3-VL Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.09,"output":0.09},"display_name":"Qwen3-VL Embedding 8B","type":"chat"},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.53,"output":0.76},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.53,"output":0.76},"display_name":"Llama 3.3 70B","type":"chat"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.18,"output":0.29},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":8192},"cost":{"input":0.53,"output":0.76},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"anyapi":{"id":"anyapi","api":"https://api.anyapi.ai/v1","name":"AnyAPI","doc":"https://docs.anyapi.ai","display_name":"AnyAPI","models":[{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"canonical_model_id":"cohere/command-r-plus-08-2024","display_name":"Command R+","type":"chat"},{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"canonical_model_id":"deepseek/deepseek-chat","display_name":"DeepSeek Chat","type":"chat"},{"id":"deepseek/deepseek-r1","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"canonical_model_id":"deepseek/deepseek-reasoner","display_name":"DeepSeek Reasoner","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"perplexity/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"canonical_model_id":"perplexity/sonar-pro","display_name":"Sonar Pro","type":"chat"},{"id":"perplexity/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"canonical_model_id":"perplexity/sonar-reasoning-pro","display_name":"Sonar Reasoning Pro","type":"chat"},{"id":"google/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-3-pro-preview","display_name":"Gemini 3 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistralai/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"mistralai/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"crusoe":{"id":"crusoe","api":"https://api.inference.crusoecloud.com/v1","name":"Crusoe","doc":"https://docs.crusoecloud.com/managed-inference/overview","display_name":"Crusoe","models":[{"id":"zai/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4.4,"cache_read":0.25},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"zai/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.25,"output":0.75,"cache_read":0.13},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4,"cache_read":0.14},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.22,"output":0.8,"cache_read":0.11},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.5,"output":1.5,"cache_read":0.25},"canonical_model_id":"deepseek/deepseek-v3-0324","display_name":"DeepSeek V3 0324","type":"chat"},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.7,"output":3.5,"cache_read":0.35},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.03},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat"},{"id":"nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.3,"output":1.83,"cache_read":0.3,"input_audio":0.5},"canonical_model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","display_name":"Nemotron 3 Nano Omni 30B A3B Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":2.4,"cache_read":0.15},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.2,"cache_read":0.05},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}}]},"volcengine-coding-plan":{"id":"volcengine-coding-plan","api":"https://ark.cn-beijing.volces.com/api/coding/v3","name":"Volcengine Ark Coding Plan","doc":"https://www.volcengine.com/docs/82379/1928261","display_name":"Volcengine Ark Coding Plan","models":[{"id":"doubao-seed-2.0-lite","name":"Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"bytedance-seed/seed-2.0-lite","display_name":"Seed 2.0 Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"doubao-seed-2.1-turbo","name":"Seed 2.1 Turbo","description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"bytedance-seed/seed-2.1-turbo","display_name":"Seed 2.1 Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"doubao-seed-evolving","name":"Seed Evolving","description":"Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"bytedance-seed/seed-evolving","display_name":"Seed Evolving","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"agentrouter":{"id":"agentrouter","api":"https://agentrouter.org/v1","name":"AgentRouter","doc":"https://agentrouter.org/docs/opencode.html","display_name":"AgentRouter","models":[{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://agentrouter.org/v1"},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://agentrouter.org/v1"},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"tencent-tokenhub":{"id":"tencent-tokenhub","api":"https://tokenhub.tencentmaas.com/v1","name":"Tencent TokenHub","doc":"https://cloud.tencent.com/document/product/1823/130050","display_name":"Tencent TokenHub","models":[{"id":"hy3-preview","name":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"tencent/hy3-preview","display_name":"Hy3 preview","type":"chat"},{"id":"hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"watsonx":{"id":"watsonx","name":"watsonx.ai","doc":"https://www.ibm.com/docs/en/watsonx/saas?topic=solutions-supported-foundation-models","display_name":"watsonx.ai","models":[{"id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B 128E Instruct FP8","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.371,"output":1.484},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B 128E Instruct FP8","type":"chat"},{"id":"meta-llama/llama-3-3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.7526,"output":0.7526},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"ibm/granite-4-h-small","name":"Granite-4.0-H-Small","description":"Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads","family":"granite","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0636,"output":0.265},"canonical_model_id":"ibm/granite-4-h-small","display_name":"Granite-4.0-H-Small","type":"chat"},{"id":"mistralai/mistral-small-3-1-24b-instruct-2503","name":"Mistral Small 3.1 24B","description":"Efficient multimodal model for instruction following, coding, reasoning, and function calling","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.106,"output":0.318},"canonical_model_id":"mistral/mistral-small-3-1-24b-instruct-2503","display_name":"Mistral Small 3.1 24B","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.159,"output":0.636},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"ambient":{"id":"ambient","api":"https://api.ambient.xyz/v1","name":"Ambient","doc":"https://ambient.xyz","display_name":"Ambient","models":[{"id":"unsloth/qwen3.8-27b-gguf","name":"qwen3.8-27b-4q","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"unsloth","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":101072,"output":101072},"cost":{"input":0.001,"output":0.001,"cache_read":0,"cache_write":0},"display_name":"qwen3.8-27b-4q","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.08,"output":0.18,"cache_read":0.016,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":0.6,"output":2,"cache_read":0.15,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ambient/small","name":"Ambient Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":101072,"output":101072},"cost":{"input":0.001,"output":0.001,"cache_read":0,"cache_write":0},"display_name":"Ambient Small","type":"chat"},{"id":"ambient/large","name":"Ambient Large","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":0.6,"output":2,"cache_read":0.15,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"Ambient Large","type":"chat"},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.2,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.69,"output":3.49,"cache_read":0.14,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.2-FP8","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.2,"output":4.2,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"zai-org/GLM-5.1-FP8","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"MiMo omni model for text, image, video, audio, and agents","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.08,"cache_write":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.23,"output":0.96,"cache_read":0.05,"cache_write":0},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.19,"output":1.14,"cache_read":0.03,"cache_write":0},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.32,"output":3.2,"cache_read":0.16,"cache_write":0},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":1,"cache_read":0.15,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-09","last_updated":"2026-10-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.09,"output":0.3,"cache_read":0.09,"cache_write":0},"display_name":"Qwen3 30B A3B Instruct 2507","type":"chat"},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.32,"output":3.2,"cache_read":0.16,"cache_write":0},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"model-oracle-ai":{"id":"model-oracle-ai","api":"https://api.modeloracle.com/api/v1","name":"Model Oracle AI","doc":"https://modeloracle.com/setup/","display_name":"Model Oracle AI","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto","name":"Auto","description":"Model Oracle AI decision engine that selects and routes among configured coding-agent models","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-29","last_updated":"2026-07-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"display_name":"Auto","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"xai":{"id":"xai","name":"xai","doc":"https://docs.x.ai/docs/models","display_name":"xai","models":[{"id":"grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"grok-imagine-video-1.5-lite","name":"Grok Imagine Video 1.5 Lite","description":"Cost-efficient video model for text-to-video and image-to-video generation","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["text","image","pdf"],"output":["video"]},"open_weights":false,"limit":{"context":1024,"output":8192},"canonical_model_id":"xai/grok-imagine-video-1.5-lite","display_name":"Grok Imagine Video 1.5 Lite","type":"chat"},{"id":"grok-imagine-image","name":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"open_weights":false,"limit":{"context":16000,"output":8192},"canonical_model_id":"xai/grok-imagine-image","display_name":"Grok Imagine Image","type":"chat"},{"id":"grok-imagine-video","name":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text","image","video","pdf"],"output":["video"]},"open_weights":false,"limit":{"context":1024,"output":8192},"display_name":"Grok Imagine Video","type":"chat"},{"id":"grok-4.3","name":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.3","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-05-30","last_updated":"2026-05-30","modalities":{"input":["text","image","audio","pdf"],"output":["video"]},"open_weights":false,"limit":{"context":1024,"output":8192},"canonical_model_id":"xai/grok-imagine-video-1.5","display_name":"Grok Imagine Video 1.5","type":"chat"},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"grok-imagine-image-quality","name":"Grok Imagine Image Quality","description":"Higher-fidelity Grok Imagine image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-03","last_updated":"2026-04-03","modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"open_weights":false,"limit":{"context":16000,"output":8192},"canonical_model_id":"xai/grok-imagine-image-quality","display_name":"Grok Imagine Image Quality","type":"chat"},{"id":"grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"display_name":"Grok Build 0.1","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"grok-4.20-multi-agent-0309","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Multi-Agent","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"grok-3-mini-fast-beta","name":"Grok 3 Mini Fast Beta","display_name":"Grok 3 Mini Fast Beta","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":120000,"output":100000},"reasoning":{"supported":true,"effort":"low","default":true},"search":{"supported":false},"type":"chat"},{"id":"grok-3-mini-beta","name":"Grok 3 Mini Beta","display_name":"Grok 3 Mini Beta","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":120000,"output":100000},"reasoning":{"supported":true,"effort":"low","default":true},"search":{"supported":false},"type":"chat"},{"id":"grok-3-fast-beta","name":"Grok 3 Fast Beta","display_name":"Grok 3 Fast Beta","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":120000,"output":100000},"reasoning":{"supported":false},"search":{"supported":false},"type":"chat"},{"id":"grok-2-vision-1212","name":"Grok 2 Vision 1212","display_name":"Grok 2 Vision 1212","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":32000,"output":32000},"reasoning":{"supported":false},"search":{"supported":false},"type":"chat"},{"id":"grok-2-image-1212","name":"Grok 2 Image 1212","display_name":"Grok 2 Image 1212","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":130000,"output":100000},"reasoning":{"supported":false},"search":{"supported":false},"type":"chat"},{"id":"grok-3-beta","name":"Grok 3 Beta","display_name":"Grok 3 Beta","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":120000,"output":100000},"reasoning":{"supported":false},"search":{"supported":false},"type":"chat"},{"id":"grok-2-1212","name":"Grok 2 1212","display_name":"Grok 2 1212","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":120000,"output":100000},"reasoning":{"supported":false},"search":{"supported":false},"type":"chat"}]},"nebius":{"id":"nebius","api":"https://api.tokenfactory.nebius.com/v1","name":"Nebius Token Factory","doc":"https://docs.tokenfactory.nebius.com/","display_name":"Nebius Token Factory","models":[{"id":"meta-models/muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":1.25},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"reflection/beam","name":"Beam 1.0 501B A23B","description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-06-30","release_date":"2026-10-05","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.25,"output":1,"cache_read":0.25},"canonical_model_id":"reflection/beam-1.0-501b-a23b","display_name":"Beam 1.0 501B A23B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-3-27b-it","name":"Gemma-3-27b-it","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-10","release_date":"2026-01-20","last_updated":"2026-02-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":110000,"input":100000,"output":8192},"cost":{"input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0.125},"display_name":"Gemma-3-27b-it","type":"chat"},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B reasoning model for coding, research, and long-horizon agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":3,"cache_read":0.45},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-01-28","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":8192},"cost":{"input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0.125},"display_name":"Qwen3-30B-A3B-Instruct-2507","type":"chat"},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2025-10-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":8192},"cost":{"input":0.2,"output":0.6},"display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen3-Embedding-8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-10","release_date":"2026-01-10","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"input":40960,"output":8192},"cost":{"input":0.01,"output":0},"display_name":"Qwen3-Embedding-8B","type":"embedding"},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-15","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":250000,"output":8192},"cost":{"input":0.6,"output":3.6,"cache_read":0.06,"cache_write":0.75},"display_name":"Qwen3.5-397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":1024000},"cost":{"input":0.14,"output":0.28,"cache_read":0.14},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":979000,"output":979000},"cost":{"input":1.32,"output":3.96,"cache_read":1.32},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"output":1048000},"cost":{"input":0.3,"output":1.2,"cache_read":0.3},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.75,"output":3.5,"cache_read":0.15},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8000},"cost":{"input":3,"output":15,"cache_read":3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8000},"cost":{"input":0.95,"output":4},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":1024000},"cost":{"input":0.15,"output":0.5,"cache_read":0.15},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":1024000},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nvidia/Nemotron-3.5-Super-VL","name":"Nemotron 3.5 Super VL 120B A12B","description":"NVIDIA vision-language reasoning model for coding, visual understanding, and agentic tool use","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.3,"output":0.9,"cache_read":0.3},"canonical_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","display_name":"Nemotron 3.5 Super VL 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron-3-Super-120B-A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.3,"output":0.9},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron-3-Super-120B-A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/Nemotron-3_5-Lightning","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.06,"output":0.24,"cache_read":0.06},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B A3B","type":"chat"},{"id":"nvidia/Nemotron-3-Ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":3,"cache_read":1},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-01-10","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":124000,"output":8192},"cost":{"input":0.15,"output":0.6,"reasoning":0.6,"cache_read":0.015,"cache_write":0.18},"display_name":"gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"NousResearch/Hermes-4-405B","name":"Hermes-4-405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-11","release_date":"2026-01-30","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":120000,"output":8192},"cost":{"input":1,"output":3,"reasoning":3,"cache_read":0.1,"cache_write":1.25},"display_name":"Hermes-4-405B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"minimax-cn":{"id":"minimax-cn","api":"https://api.minimax.cn/anthropic/v1","name":"MiniMax (minimax.cn)","doc":"https://platform.minimaxi.com/docs/guides/quickstart","display_name":"MiniMax (minimax.cn)","models":[{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"display_name":"MiniMax-M2","type":"chat"},{"id":"MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"display_name":"MiniMax-M2.5-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"scaleway":{"id":"scaleway","api":"https://api.scaleway.ai/v1","name":"Scaleway","doc":"https://www.scaleway.com/en/docs/generative-apis/","display_name":"Scaleway","models":[{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"status":"beta","cost":{"input":0.684,"output":3.762,"reasoning":3.762,"cache_read":0.137},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"status":"beta","cost":{"input":0.468,"output":0.936,"reasoning":0.936,"cache_read":0.0936},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":260000,"output":16384},"cost":{"input":0.75,"output":2.25,"reasoning":8.4},"canonical_model_id":"alibaba/qwen3-235b-a22b","display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"whisper-large-v3","name":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2023-09","release_date":"2023-09-01","last_updated":"2026-03-17","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.003,"output":0},"display_name":"Whisper Large v3","type":"chat"},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"status":"beta","cost":{"input":0.672,"output":2.016,"reasoning":2.016,"cache_read":0.134},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"bge-multilingual-gemma2","name":"BGE Multilingual Gemma2","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-07-26","last_updated":"2025-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.1,"output":0},"display_name":"BGE Multilingual Gemma2","type":"chat"},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.2,"output":0.8},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-01","last_updated":"2026-05-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"status":"beta","cost":{"input":0.25,"output":0.5},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"output":16384},"cost":{"input":0.9,"output":0.9},"display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-05-01","last_updated":"2026-05-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"status":"beta","cost":{"input":0.25,"output":1.5},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"pixtral-12b-2409","name":"Pixtral 12B 2409","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-25","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.2,"output":0.2},"canonical_model_id":"mistral/pixtral-12b","display_name":"Pixtral 12B 2409","type":"chat"},{"id":"qwen3-embedding-8b","name":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-05","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.1,"output":0},"display_name":"Qwen3 Embedding 8B","type":"embedding"},{"id":"mistral-medium-3.5-128b","name":"Mistral Medium 3.5 128B","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5 128B","type":"chat"},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":1.8,"output":5.5},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-small-3.2-24b-instruct-2506","name":"Mistral Small 3.2 24B Instruct (2506)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.15,"output":0.35},"canonical_model_id":"mistral/mistral-small-2506","display_name":"Mistral Small 3.2 24B Instruct (2506)","type":"chat"},{"id":"gpt-oss-120b","name":"GPT-OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.15,"output":0.6},"display_name":"GPT-OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"status":"beta","cost":{"input":2.01,"output":6.15},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"vercel":{"id":"vercel","name":"Vercel AI Gateway","doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","display_name":"Vercel AI Gateway","models":[{"id":"voyage/rerank-3-lite","name":"Voyage Rerank 3 Lite","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-30","last_updated":"2026-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"display_name":"Voyage Rerank 3 Lite","type":"chat"},{"id":"voyage/voyage-law-2","name":"voyage-law-2","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-04-15","last_updated":"2024-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"voyage-law-2","type":"chat"},{"id":"voyage/rerank-2.5-lite","name":"Voyage Rerank 2.5 Lite","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"display_name":"Voyage Rerank 2.5 Lite","type":"chat"},{"id":"voyage/voyage-3.5","name":"voyage-3.5","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"voyage-3.5","type":"chat"},{"id":"voyage/rerank-3","name":"Voyage Rerank 3","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-30","last_updated":"2026-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"display_name":"Voyage Rerank 3","type":"chat"},{"id":"voyage/voyage-finance-2","name":"voyage-finance-2","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-06-03","last_updated":"2024-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"voyage-finance-2","type":"chat"},{"id":"voyage/voyage-4-large","name":"voyage-4-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"display_name":"voyage-4-large","type":"chat"},{"id":"voyage/voyage-3.5-lite","name":"voyage-3.5-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"voyage-3.5-lite","type":"chat"},{"id":"voyage/voyage-4","name":"voyage-4","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"display_name":"voyage-4","type":"chat"},{"id":"voyage/voyage-3-large","name":"voyage-3-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-01-07","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"voyage-3-large","type":"chat"},{"id":"voyage/voyage-code-2","name":"voyage-code-2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-01-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"voyage-code-2","type":"chat"},{"id":"voyage/voyage-code-3","name":"voyage-code-3","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-12-04","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"voyage-code-3","type":"chat"},{"id":"voyage/rerank-2.5","name":"Voyage Rerank 2.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"display_name":"Voyage Rerank 2.5","type":"chat"},{"id":"voyage/voyage-4-lite","name":"voyage-4-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"voyage","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"display_name":"voyage-4-lite","type":"chat"},{"id":"interfaze/interfaze-beta","name":"Interfaze Beta","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"temperature":true,"release_date":"2025-10-07","last_updated":"2026-04-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":1.5,"output":3.5},"display_name":"Interfaze Beta","type":"chat"},{"id":"stealth/glyph-cluster","name":"Glyph Cluster","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0},"display_name":"Glyph Cluster","type":"chat"},{"id":"stealth/cat-jam","name":"Cat Jam","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"display_name":"Cat Jam","type":"chat"},{"id":"zai/glm-4.5","name":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":96000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"zai/glm-5v-turbo","name":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM 5V Turbo","type":"chat"},{"id":"zai/glm-5.3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131000},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.6","name":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":96000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"zai/glm-5.2-fast","name":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":2.8,"output":8.8,"cache_read":0.56},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 Fast","type":"chat"},{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131100},"cost":{"input":1,"output":3.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-4.5v","name":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":66000,"output":16000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM 4.5V","type":"chat"},{"id":"zai/glm-5.3-flashx","name":"GLM 5.3 FlashX","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.37,"output":1.25,"cache_read":0.075},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 FlashX","type":"chat"},{"id":"zai/glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131000},"cost":{"input":0.07,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM 4.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.7","name":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":120000},"cost":{"input":0.6,"output":2.2},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.8,"output":2.55,"cache_read":0.16},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5.1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":64000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.7-flashx","name":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flashx","display_name":"GLM 4.7 FlashX","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"zai/glm-5-turbo","name":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM 5 Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.5-air","name":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":96000},"cost":{"input":0.2,"output":1.1,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM 4.5 Air","type":"chat"},{"id":"zai/glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5.3-fast","name":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":2.1,"output":6.6,"cache_read":0.21},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 Fast","type":"chat"},{"id":"spacexai/grok-4.20-multi-agent","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Multi-Agent","type":"chat"},{"id":"spacexai/grok-tts","name":"Grok TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Grok TTS","type":"chat"},{"id":"spacexai/grok-4.20-reasoning","name":"Grok 4.20 Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Reasoning","type":"chat"},{"id":"spacexai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"spacexai/grok-imagine-video-1.5-lite","name":"Grok Imagine Video 1.5 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"canonical_model_id":"xai/grok-imagine-video-1.5-lite","display_name":"Grok Imagine Video 1.5 Lite","type":"chat"},{"id":"spacexai/grok-voice-think-fast-1.0","name":"Grok Voice Think Fast 1.0","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Grok Voice Think Fast 1.0","type":"chat"},{"id":"spacexai/grok-4.20-non-reasoning","name":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Non-Reasoning","type":"chat"},{"id":"spacexai/grok-stt","name":"Grok STT","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Grok STT","type":"chat"},{"id":"spacexai/grok-imagine-image","name":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"canonical_model_id":"xai/grok-imagine-image","display_name":"Grok Imagine Image","type":"chat"},{"id":"spacexai/grok-imagine-video","name":"Grok Imagine","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Grok Imagine","type":"chat"},{"id":"spacexai/grok-4.1-fast-reasoning","name":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"xai/grok-4.1-fast-reasoning","display_name":"Grok 4.1 Fast Reasoning","type":"chat"},{"id":"spacexai/grok-4.3","name":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"spacexai/grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-05-30","last_updated":"2026-05-30","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"canonical_model_id":"xai/grok-imagine-video-1.5","display_name":"Grok Imagine Video 1.5","type":"chat"},{"id":"spacexai/grok-4.5","name":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"spacexai/grok-voice-think-fast-2.0","name":"Grok Voice Think Fast 2.0","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Grok Voice Think Fast 2.0","type":"chat"},{"id":"spacexai/grok-imagine-image-2.0","name":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"canonical_model_id":"xai/grok-imagine-image-2.0","display_name":"Grok Imagine Image 2.0","type":"chat"},{"id":"spacexai/grok-4.20-multi-agent-beta","name":"Grok 4.20 Multi Agent Beta","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Multi Agent Beta","type":"chat"},{"id":"spacexai/grok-4.20-non-reasoning-beta","name":"Grok 4.20 Beta Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.4,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Beta Non-Reasoning","type":"chat"},{"id":"spacexai/grok-build-0.1","name":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"spacexai/grok-4.1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast Non-Reasoning","type":"chat"},{"id":"spacexai/grok-4.20-reasoning-beta","name":"Grok 4.20 Beta Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"display_name":"Grok 4.20 Beta Reasoning","type":"chat"},{"id":"spacexai/grok-4.6","name":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"prodia/flux-fast-schnell","name":"Flux Schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-08-02","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"Flux Schnell","type":"chat"},{"id":"recraft/recraft-v2","name":"Recraft V2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-03-13","last_updated":"2024-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"Recraft V2","type":"chat"},{"id":"recraft/recraft-v4-pro","name":"Recraft V4 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Recraft V4 Pro","type":"chat"},{"id":"recraft/recraft-v4.1-utility","name":"Recraft V4.1 Utility","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Recraft V4.1 Utility","type":"chat"},{"id":"recraft/recraft-v4.1-pro","name":"Recraft V4.1 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Recraft V4.1 Pro","type":"chat"},{"id":"recraft/recraft-v3","name":"Recraft V3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-10-30","last_updated":"2024-10","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"Recraft V3","type":"chat"},{"id":"recraft/recraft-v4.1","name":"Recraft V4.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Recraft V4.1","type":"chat"},{"id":"recraft/recraft-v4.1-flash","name":"Recraft V4.1 Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Recraft V4.1 Flash","type":"chat"},{"id":"recraft/recraft-v4.1-utility-pro","name":"Recraft V4.1 Utility Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Recraft V4.1 Utility Pro","type":"chat"},{"id":"recraft/recraft-v4","name":"Recraft V4","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Recraft V4","type":"chat"},{"id":"poolside/laguna-s-2.1-free","name":"Laguna S 2.1 Free","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.09,"output":0.18,"cache_read":0.009},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100001}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-5.5-fast","name":"Claude Opus 5.5 (Fast)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":8,"output":40,"cache_read":0.4,"cache_write":10},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (Fast)","type":"chat"},{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4.8-fast","name":"Claude Opus 4.8 (Fast)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"anthropic/claude-opus-5-fast","name":"Claude Opus 5 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (Fast)","type":"chat"},{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"cohere/rerank-v4-fast","name":"Cohere Rerank 4 Fast","description":"Reranking model for improving retrieval quality in search and recommendation systems","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"display_name":"Cohere Rerank 4 Fast","type":"chat"},{"id":"cohere/rerank-v4-pro","name":"Cohere Rerank 4 Pro","description":"Reranking model for improving retrieval quality in search and recommendation systems","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"display_name":"Cohere Rerank 4 Pro","type":"chat"},{"id":"cohere/command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a","display_name":"Command A","type":"chat"},{"id":"cohere/embed-v4.0","name":"Embed v4.0","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":1536},"display_name":"Embed v4.0","type":"chat"},{"id":"cohere/embed-v5.0-pro","name":"Embed 5 Pro","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-30","last_updated":"2026-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"Embed 5 Pro","type":"chat"},{"id":"cohere/embed-v5.0-fast","name":"Embed 5 Fast","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-30","last_updated":"2026-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"Embed 5 Fast","type":"chat"},{"id":"cohere/rerank-v3.5","name":"Cohere Rerank 3.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":4096},"display_name":"Cohere Rerank 3.5","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.076,"output":0.153,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash-1017-fast","name":"DeepSeek V4.1 Flash 1017 Fast","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":0.6,"output":2.4,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017 Fast","type":"chat"},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.075,"output":0.3,"cache_read":0.0015},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.2156,"output":0.6468,"cache_read":0.0068},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.066},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v3.2-thinking","name":"DeepSeek V3.2 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8000},"cost":{"input":0.62,"output":1.85},"display_name":"DeepSeek V3.2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"deepseek/deepseek-v4.1-flash-fast","name":"DeepSeek V4.1 Flash Fast","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.6,"output":2.4,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash Fast","type":"chat"},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":128000},"cost":{"input":0.25,"output":0.95,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek-V3.1","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8000},"cost":{"input":0.62,"output":1.85},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":0.075,"output":0.3,"cache_read":0.0015},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.13,"output":0.26,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-r1","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":1.35,"output":5.4},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"quiverai/arrow-2","name":"Arrow 2","description":"Fast SVG generation model for creation, vectorization, editing, and animation","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"release_date":"2026-09-16","last_updated":"2026-09-16","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"canonical_model_id":"quiverai/arrow-2","display_name":"Arrow 2","type":"chat"},{"id":"quiverai/arrow-2-telos","name":"Arrow 2 Telos","description":"High-fidelity SVG generation model for complex vector work and long-context refinement","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"release_date":"2026-09-16","last_updated":"2026-09-16","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":6,"output":30,"cache_read":0.6,"cache_write":7.5},"canonical_model_id":"quiverai/arrow-2-telos","display_name":"Arrow 2 Telos","type":"chat"},{"id":"bfl/flux-kontext-max","name":"FLUX.1 Kontext Max","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-05-29","last_updated":"2025-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"FLUX.1 Kontext Max","type":"image-generation"},{"id":"bfl/flux-pro-1.1-ultra","name":"FLUX1.1 [pro] Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-11-01","last_updated":"2024-11","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"FLUX1.1 [pro] Ultra","type":"chat"},{"id":"bfl/flux-3-image","name":"FLUX 3 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-05","last_updated":"2026-10-05","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"FLUX 3 Image","type":"chat"},{"id":"bfl/flux-3-video","name":"Flux 3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-04","last_updated":"2026-08-04","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Flux 3","type":"chat"},{"id":"bfl/flux-3-image-klein","name":"FLUX 3 Image Klein","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"FLUX 3 Image Klein","type":"chat"},{"id":"bfl/flux-2-flex","name":"FLUX.2 [flex]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"FLUX.2 [flex]","type":"image-generation"},{"id":"bfl/flux-2-klein-4b","name":"FLUX.2 [klein] 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"FLUX.2 [klein] 4B","type":"chat"},{"id":"bfl/flux-pro-1.0-fill","name":"FLUX.1 Fill [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-10-01","last_updated":"2024-10","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"FLUX.1 Fill [pro]","type":"chat"},{"id":"bfl/flux-2-klein-9b","name":"FLUX.2 [klein] 9B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"FLUX.2 [klein] 9B","type":"chat"},{"id":"bfl/flux-2-pro","name":"FLUX.2 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":67300,"output":67300},"display_name":"FLUX.2 [pro]","type":"image-generation"},{"id":"bfl/flux-2-max","name":"FLUX.2 [max]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":67300,"output":67300},"display_name":"FLUX.2 [max]","type":"chat"},{"id":"bfl/flux-pro-1.1","name":"FLUX1.1 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-10-02","last_updated":"2024-10","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"FLUX1.1 [pro]","type":"chat"},{"id":"bfl/flux-kontext-pro","name":"FLUX.1 Kontext Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-05-29","last_updated":"2025-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":8192},"display_name":"FLUX.1 Kontext Pro","type":"chat"},{"id":"tencent/hy-mt2-lite","name":"Tencent Hy-MT2-Lite","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":4000},"cost":{"input":0.044,"output":0.177},"display_name":"Tencent Hy-MT2-Lite","type":"chat"},{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy-mt2-plus","name":"Tencent Hy-MT2-Plus","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":4000},"cost":{"input":0.074,"output":0.295},"display_name":"Tencent Hy-MT2-Plus","type":"chat"},{"id":"tencent/hy-mt2-pro","name":"Tencent Hy-MT2-Pro","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":4000},"cost":{"input":0.074,"output":0.295},"display_name":"Tencent Hy-MT2-Pro","type":"chat"},{"id":"tencent/hy4-preview","name":"Tencent Hy4 Preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Tencent Hy4 Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"heygen/heygen-video-1","name":"HeyGen Video","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-09","last_updated":"2026-10-09","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"HeyGen Video","type":"chat"},{"id":"reflection/beam","name":"Beam 1.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"display_name":"Beam 1.0","type":"chat"},{"id":"reflection/beam-free","name":"Beam 1.0 (Free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"display_name":"Beam 1.0 (Free)","type":"chat"},{"id":"inference-net/schematron-v2-small","name":"Schematron V2 Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.05,"output":0.23,"cache_read":0.05},"display_name":"Schematron V2 Small","type":"chat"},{"id":"inference-net/schematron-v2-turbo","name":"Schematron V2 Turbo","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.03,"output":0.15,"cache_read":0.03},"display_name":"Schematron V2 Turbo","type":"chat"},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat"},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"meituan/longcat-2.5-preview","name":"LongCat 2.5 Preview","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"longcat","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-09-26","last_updated":"2026-09-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"display_name":"LongCat 2.5 Preview","type":"chat"},{"id":"perplexity/pplx-embed-v1-4b","name":"Embed v1 4b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"display_name":"Embed v1 4b","type":"chat"},{"id":"perplexity/pplx-embed-v1-0.6b","name":"Embed v1 0.6b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"v0","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"display_name":"Embed v1 0.6b","type":"chat"},{"id":"perplexity/sonar","name":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-02","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":8000},"cost":{"input":0.25,"output":2.5,"cache_write":0.0625},"display_name":"Sonar","type":"chat"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat"},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"muse","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/llama-3.1-8b","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.22,"output":0.22},"display_name":"Llama 3.1 8B Instruct","type":"chat"},{"id":"meta/llama-3.1-70b","name":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.72,"output":0.72},"display_name":"Llama 3.1 70B Instruct","type":"chat"},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-image-1.0","name":"Muse Image 1.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"muse","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Muse Image 1.0","type":"chat"},{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.2 Contributor","type":"chat"},{"id":"meta/muse-wonder-1.0","name":"Muse Wonder","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"meta/muse-wonder-1.0","display_name":"Muse Wonder","type":"chat"},{"id":"meta/muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.3 Contributor","type":"chat"},{"id":"meta/muse-spark-open","name":"Muse Spark Open","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"meta/llama-3.3-70b","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"meta/llama-4-maverick","name":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama-4-Maverick-17B-128E-Instruct-FP8","type":"chat"},{"id":"meta/llama-4-scout","name":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama-4-Scout-17B-16E-Instruct-FP8","type":"chat"},{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":80000},"cost":{"input":0.25,"output":0.8},"canonical_model_id":"arcee-ai/trinity-large-thinking","display_name":"Trinity Large Thinking","type":"chat"},{"id":"alibaba/qwen3.5-flash","name":"Qwen 3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen-3-32b","name":"Qwen 3.32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.15,"output":0.6},"display_name":"Qwen 3.32B","type":"chat"},{"id":"alibaba/wan-v2.6-t2v","name":"Wan v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.6 Text-to-Video","type":"chat"},{"id":"alibaba/qwen3.7-max","name":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen 3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"alibaba/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":1}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-thinking","display_name":"Qwen3 Next 80B A3B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.8-max","name":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max-preview","display_name":"Qwen 3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.2},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"alibaba/qwen3-vl-instruct","name":"Qwen3 VL Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"display_name":"Qwen3 VL Instruct","type":"chat"},{"id":"alibaba/qwen3-coder","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-22","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.22,"output":1.8,"cache_read":0.022,"tiers":[{"input":2.7,"output":13.5,"cache_read":0.54,"tier":{"type":"context","size":32001}},{"input":4.5,"output":22.5,"cache_read":0.9,"tier":{"type":"context","size":128001}}]},"display_name":"Qwen3 Coder 480B A35B Instruct","type":"chat"},{"id":"alibaba/qwen3.5-plus","name":"Qwen 3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":256001}}],"context_over_200k":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625}},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen 3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/wan-v2.6-i2v-flash","name":"Wan v2.6 Image-to-Video Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.6 Image-to-Video Flash","type":"chat"},{"id":"alibaba/wan-v2.6-r2v-flash","name":"Wan v2.6 Reference-to-Video Flash","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.6 Reference-to-Video Flash","type":"chat"},{"id":"alibaba/qwen-3-14b","name":"Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.24},"display_name":"Qwen3-14B","type":"chat"},{"id":"alibaba/qwen3.7-flash","name":"Qwen 3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"tiers":[{"input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0.125,"tier":{"type":"context","size":32000}},{"input":0.2,"output":0.8,"cache_read":0.04,"cache_write":0.25,"tier":{"type":"context","size":256000}}]},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3-embedding-0.6b","name":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"display_name":"Qwen3 Embedding 0.6B","type":"embedding"},{"id":"alibaba/qwen-3-30b","name":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.5},"display_name":"Qwen3-30B-A3B","type":"chat"},{"id":"alibaba/qwen3.8-omni-flash","name":"Qwen 3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen 3.8 Omni Flash","type":"chat"},{"id":"alibaba/qwen3-coder-30b-a3b","name":"Qwen 3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-31","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.6},"display_name":"Qwen 3 Coder 30B A3B Instruct","type":"chat"},{"id":"alibaba/qwen3-embedding-4b","name":"Qwen3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"display_name":"Qwen3 Embedding 4B","type":"embedding"},{"id":"alibaba/wan-v2.6-i2v","name":"Wan v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.6 Image-to-Video","type":"chat"},{"id":"alibaba/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262114,"output":262114},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3 Next 80B A3B Instruct","type":"chat"},{"id":"alibaba/wan-v2.5-t2v-preview","name":"Wan v2.5 Text-to-Video Preview","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.5 Text-to-Video Preview","type":"chat"},{"id":"alibaba/qwen3-max-thinking","name":"Qwen 3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-23","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":1.2,"output":6,"cache_read":0.24,"tiers":[{"input":2.4,"output":12,"cache_read":0.48,"tier":{"type":"context","size":32001}},{"input":3,"output":15,"cache_read":0.6,"tier":{"type":"context","size":128001}}]},"display_name":"Qwen 3 Max Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.8-max-prime","name":"Qwen 3.8 Max Prime","description":"High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows","family":"qwen3.8-max","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":4,"output":12,"cache_read":0.5,"cache_write":5},"canonical_model_id":"alibaba/qwen3.8-max-prime","display_name":"Qwen 3.8 Max Prime","type":"chat"},{"id":"alibaba/qwen3.8-flash","name":"Qwen 3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":128000},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/qwen3-embedding-8b","type":"embedding","name":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"canonical_model_id":"alibaba/qwen3-embedding-8b","display_name":"Qwen3 Embedding 8B"},{"id":"alibaba/wan-v3.0-video","name":"Wan v3.0 Video","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-23","last_updated":"2026-08-23","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v3.0 Video","type":"chat"},{"id":"alibaba/wan-v2.7-r2v","name":"Wan v2.7 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.7 Reference-to-Video","type":"chat"},{"id":"alibaba/wan-v3.0-video-prime","name":"Wan v3.0 Video Prime","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v3.0 Video Prime","type":"chat"},{"id":"alibaba/qwen3.6-27b","name":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen 3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen-3-235b","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.22,"output":0.88},"display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"alibaba/qwen3.6-plus","name":"Qwen 3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen 3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba/qwen3.7-plus","name":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.24,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.24,"cache_write":1.5}},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen 3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"alibaba/wan-v2.6-r2v","name":"Wan v2.6 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.6 Reference-to-Video","type":"chat"},{"id":"alibaba/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"alibaba/wan-v2.7-t2v","name":"Wan v2.7 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wan v2.7 Text-to-Video","type":"chat"},{"id":"mixedbread/toast-1","name":"Toast 1","description":"Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis","attachment":false,"reasoning":{"supported":false},"tool_call":true,"release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":4000},"cost":{"input":0.3,"output":0.72,"cache_read":0.036},"canonical_model_id":"mixedbread/toast-1","display_name":"Toast 1","type":"chat"},{"id":"elorian/glimpse","name":"Glimpse","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":false,"release_date":"2026-10-16","last_updated":"2026-10-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":220000,"output":4096},"cost":{"input":0.6,"output":3,"cache_read":0.06},"display_name":"Glimpse","type":"chat"},{"id":"klingai/kling-v2.6-t2v","name":"Kling v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v2.6 Text-to-Video","type":"chat"},{"id":"klingai/kling-v2.6-i2v","name":"Kling v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v2.6 Image-to-Video","type":"chat"},{"id":"klingai/kling-v2.5-turbo-t2v","name":"Kling v2.5 Turbo Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v2.5 Turbo Text-to-Video","type":"chat"},{"id":"klingai/kling-v3.0-i2v","name":"Kling v3.0 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v3.0 Image-to-Video","type":"chat"},{"id":"klingai/kling-v3.0-motion-control","name":"Kling v3.0 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v3.0 Motion Control","type":"chat"},{"id":"klingai/kling-v3.0-t2v","name":"Kling v3.0 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v3.0 Text-to-Video","type":"chat"},{"id":"klingai/kling-v2.6-motion-control","name":"Kling v2.6 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v2.6 Motion Control","type":"chat"},{"id":"klingai/kling-v2.5-turbo-i2v","name":"Kling v2.5 Turbo Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Kling v2.5 Turbo Image-to-Video","type":"chat"},{"id":"bytedance/seedream-5.0-lite","name":"Seedream 5.0 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedream 5.0 Lite","type":"chat"},{"id":"bytedance/seedream-4.5","name":"Seedream 4.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-11-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedream 4.5","type":"chat"},{"id":"bytedance/seed-1.8","name":"Seed 1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-01","last_updated":"2025-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32768},"cost":{"input":0.25,"output":2,"cache_read":0.05,"tiers":[{"input":0.5,"output":4,"cache_read":0.05,"tier":{"type":"context","size":128001}}]},"display_name":"Seed 1.8","type":"chat"},{"id":"bytedance/seed-2.1-turbo","name":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.5,"cache_read":0.1},"display_name":"Seed 2.1 Turbo","type":"chat"},{"id":"bytedance/seedream-4.0","name":"Seedream 4.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-09-09","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedream 4.0","type":"chat"},{"id":"bytedance/seedance-v1.0-pro","name":"Seedance v1.0 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-06-11","last_updated":"2025-06-11","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedance v1.0 Pro","type":"chat"},{"id":"bytedance/seedance-2.0","name":"Seedance 2.0","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedance 2.0","type":"chat"},{"id":"bytedance/seedance-2.0-fast","name":"Seedance 2.0 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedance 2.0 Fast","type":"chat"},{"id":"bytedance/seedance-v1.5-pro","name":"Seedance v1.5 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedance v1.5 Pro","type":"chat"},{"id":"bytedance/seedance-2.0-mini","name":"Seedance 2.0 Mini","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-06-22","last_updated":"2026-06-22","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedance 2.0 Mini","type":"chat"},{"id":"bytedance/seedance-2.5","name":"Seedance 2.5","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedance 2.5","type":"chat"},{"id":"bytedance/seedance-v1.0-pro-fast","name":"Seedance v1.0 Pro Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-24","last_updated":"2025-10-31","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedance v1.0 Pro Fast","type":"chat"},{"id":"bytedance/seedream-5.0-pro","name":"Seedream 5.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-11","last_updated":"2026-07-11","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Seedream 5.0 Pro","type":"chat"},{"id":"bytedance/seed-1.6","name":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-01","last_updated":"2025-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.25,"output":2,"cache_read":0.05,"tiers":[{"input":0.5,"output":4,"cache_read":0.05,"tier":{"type":"context","size":128001}}]},"display_name":"Seed 1.6","type":"chat"},{"id":"liquid/lfm2.5-24b-a2b","name":"LFM2.5-24B-A2B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"liquid","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8200},"cost":{"input":0.05,"output":0.7,"cache_read":0.025},"display_name":"LFM2.5-24B-A2B","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":false,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":57920},"cost":{"input":1.5,"output":9},"canonical_model_id":"google/gemini-omni-flash-preview","display_name":"Gemini Omni Flash Preview","type":"chat"},{"id":"google/gemini-3.1-flash-image-preview","name":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3.1-flash-image-preview","display_name":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.5-transcribe-live","name":"Gemini 3.5 Transcribe Live","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"canonical_model_id":"google/gemini-3.5-transcribe-live","display_name":"Gemini 3.5 Transcribe Live","type":"chat"},{"id":"google/gemini-2.5-flash-image","name":"Nano Banana (Gemini 2.5 Flash Image)","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Nano Banana (Gemini 2.5 Flash Image)","type":"image-generation"},{"id":"google/gemini-3.8-flash-lite-tts","name":"Gemini 3.8 Flash-Lite TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.5,"output":6},"display_name":"Gemini 3.8 Flash-Lite TTS","type":"chat"},{"id":"google/text-multilingual-embedding-002","name":"Text Multilingual Embedding 002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-03-01","last_updated":"2024-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"Text Multilingual Embedding 002","type":"chat"},{"id":"google/gemini-embedding-2","name":"Gemini Embedding 2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"canonical_model_id":"google/gemini-embedding-2","display_name":"Gemini Embedding 2","type":"embedding"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/veo-3.1-lite-generate-001","name":"Veo 3.1 Lite Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Veo 3.1 Lite Generate","type":"chat"},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200001}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/veo-3.1-fast-generate-001","name":"Veo 3.1 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Veo 3.1 Fast Generate","type":"chat"},{"id":"google/gemini-3-flash","name":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.5,"output":3,"cache_read":0.05},"display_name":"Gemini 3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.5,"output":9,"cache_read":0.15},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/veo-3.0-fast-generate-001","name":"Veo 3.0 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-07-31","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Veo 3.0 Fast Generate","type":"chat"},{"id":"google/gemini-3.8-live","name":"Gemini 3.8 Live","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-15","last_updated":"2026-09-15","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.75,"output":4.5},"display_name":"Gemini 3.8 Live","type":"chat"},{"id":"google/veo-3.1-generate-001","name":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Veo 3.1","type":"chat"},{"id":"google/gemini-3.1-flash-lite-image","name":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":1.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.1-flash-lite-image","display_name":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/text-embedding-005","name":"Text Embedding 005","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-08-01","last_updated":"2024-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"Text Embedding 005","type":"chat"},{"id":"google/gemini-3.5-transcribe","name":"Gemini 3.5 Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":2,"output":12},"display_name":"Gemini 3.5 Transcribe","type":"chat"},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"canonical_model_id":"google/gemini-embedding-001","display_name":"Gemini Embedding 001","type":"embedding"},{"id":"google/gemini-3.8-flash-tts","name":"Gemini 3.8 Flash TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.5,"output":9},"display_name":"Gemini 3.8 Flash TTS","type":"chat"},{"id":"google/gemini-3.8-live-extended-thinking","name":"Gemini 3.8 Live Extended Thinking","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-15","last_updated":"2026-09-15","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.75,"output":4.5},"display_name":"Gemini 3.8 Live Extended Thinking","type":"chat"},{"id":"google/veo-3.0-generate-001","name":"Veo 3.0","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-05-20","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Veo 3.0","type":"chat"},{"id":"google/gemini-nano-banana-2.1","name":"Gemini Nano Banana 2.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-nano-banana-2.1","display_name":"Gemini Nano Banana 2.1","type":"image-generation"},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Gemini multimodal model for text, image, audio, video, and document tasks","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.25,"output":1.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"callstack/apex","name":"Apex","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"release_date":"2026-10-08","last_updated":"2026-10-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.2},"display_name":"Apex","type":"chat"},{"id":"fireworks/ember-1","name":"Ember-1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"display_name":"Ember-1","type":"chat"},{"id":"sakana/fugu-max","name":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"sakana/fugu-max","display_name":"Fugu Max","type":"chat"},{"id":"sakana/fugu-ultra-v2","name":"Fugu Ultra v2","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-08-28","release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"sakana/fugu-ultra-v2","display_name":"Fugu Ultra v2","type":"chat"},{"id":"sakana/namazu","name":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.15},"display_name":"Sakana Namazu","type":"chat"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"inclusionai/ling-3.0-flash","name":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.021,"output":0.063,"cache_read":0.0042},"display_name":"Ling 3.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionai/ling-3.1-flash","name":"Ling 3.1 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.06},"canonical_model_id":"inclusionai/ling-3.1-flash","display_name":"Ling 3.1 Flash","type":"chat"},{"id":"inclusionai/ling-3.0-flash-sante","name":"Ling 3.0 Flash Sante","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"display_name":"Ling 3.0 Flash Sante","type":"chat"},{"id":"inclusionai/ling-3.0-flash-vl","name":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"display_name":"Ling 3.0 Flash VL","type":"chat"},{"id":"inclusionai/ling-3.0-flash-fin","name":"Ling 3.0 Flash Fin","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-08-27","last_updated":"2026-09-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"canonical_model_id":"inclusionai/ling-3.0-flash-fin","display_name":"Ling 3.0 Flash Fin","type":"chat"},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k3-fast","name":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 Fast","type":"chat"},{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code High Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code High Speed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.6,"output":3},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2","name":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12-31","release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.57,"output":2.3},"canonical_model_id":"moonshotai/kimi-k2","display_name":"Kimi K2 Instruct","type":"chat"},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"topaz/proteus","name":"Proteus","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Proteus","type":"chat"},{"id":"topaz/wonder-3.5","name":"Wonder 3.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Wonder 3.5","type":"chat"},{"id":"topaz/starlight-precise-2.6","name":"Starlight Precise 2.6","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Starlight Precise 2.6","type":"chat"},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.025},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-nano-9b-v2","name":"Nvidia Nemotron Nano 9B V2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.06,"output":0.23},"canonical_model_id":"nvidia/nemotron-nano-9b-v2","display_name":"Nvidia Nemotron Nano 9B V2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":false,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.15,"output":0.65},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"NVIDIA Nemotron 3 Super 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.2,"output":0.5,"cache_read":0.04},"display_name":"NVIDIA Nemotron 3.5 Super VL","type":"chat"},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-lightning-free","name":"Nemotron 3.5 Lightning Free","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65000},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"Nvidia Nemotron Nano 12B V2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.2,"output":0.6},"canonical_model_id":"nvidia/nemotron-nano-12b-v2-vl","display_name":"Nvidia Nemotron Nano 12B V2 VL","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xiaomi/mimo-v2.6-pro","name":"MiMo V2.6 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo V2.6 Pro","type":"chat"},{"id":"xiaomi/mimo-v2.5","name":"MiMo M2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131100},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo M2.5","type":"chat"},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","name":"MiMo V2.6 Pro UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":4.35,"output":8.7,"cache_read":0.036},"canonical_model_id":"xiaomi/mimo-v2.6-pro-ultraspeed","display_name":"MiMo V2.6 Pro UltraSpeed","type":"chat"},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131000},"cost":{"input":0.3045,"output":0.609,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro","type":"chat"},{"id":"xiaomi/mimo-v2.6-flash","name":"MiMo V2.6 Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo V2.6 Flash","type":"chat"},{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-23","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375},"display_name":"MiniMax M2.1 Lightning","type":"chat"},{"id":"minimax/minimax-h3","name":"MiniMax H3","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"minimax","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-07-31","last_updated":"2026-10-04","modalities":{"input":["text","image"],"output":["video"]},"open_weights":true,"limit":{"context":8192,"output":8192},"canonical_model_id":"minimax/MiniMax-H3","display_name":"MiniMax H3","type":"chat"},{"id":"minimax/minimax-m2.7","name":"Minimax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"Minimax M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-h3-max","name":"MiniMax H3 Max","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"minimax","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"MiniMax H3 Max","type":"chat"},{"id":"minimax/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 High Speed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax M2.7 High Speed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5 High Speed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5-highspeed","display_name":"MiniMax M2.5 High Speed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"minimax/minimax-m2","name":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":196608},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax M2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"stepfun/step-5-preview","name":"Step 5 Preview","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":2.7,"cache_read":0.1},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"inception/mercury-coder-small","name":"Mercury Coder Small Beta","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"mercury","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-02-26","last_updated":"2025-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":16384},"cost":{"input":0.25,"output":1},"display_name":"Mercury Coder Small Beta","type":"chat"},{"id":"inception/mercury-2.5","name":"Mercury 2.5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":260000,"output":65536},"cost":{"input":0.04,"output":0.15,"cache_read":0.004},"display_name":"Mercury 2.5","type":"chat"},{"id":"inception/mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-24","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.024999999999999998},"display_name":"Mercury 2","type":"chat"},{"id":"amazon/titan-embed-text-v2","name":"Titan Text Embeddings V2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"titan-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-04-30","last_updated":"2024-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"Titan Text Embeddings V2","type":"chat"},{"id":"amazon/nova-2-lite","name":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-02","last_updated":"2024-12-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.075},"display_name":"Nova 2 Lite","type":"chat"},{"id":"amazon/nova-lite","name":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite","type":"chat"},{"id":"amazon/nova-pro","name":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8},"canonical_model_id":"amazon/nova-pro","display_name":"Nova Pro","type":"chat"},{"id":"amazon/nova-micro","name":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035},"canonical_model_id":"amazon/nova-micro","display_name":"Nova Micro","type":"chat"},{"id":"mistral/codestral-embed","name":"Codestral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"codestral-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"Codestral Embed","type":"chat"},{"id":"mistral/mistral-nemo","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-07-18","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.029,"output":0.03},"display_name":"Mistral Nemo","type":"chat"},{"id":"mistral/mistral-large-4","name":"Mistral Large 4","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":262144},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"display_name":"Mistral Large 4","type":"chat"},{"id":"mistral/mistral-medium-3.5","name":"Mistral Medium Latest","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-05-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":256000},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"display_name":"Mistral Medium Latest","type":"chat"},{"id":"mistral/mistral-small","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2024-09-17","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Mistral Small (latest)","type":"chat"},{"id":"mistral/mistral-large-3","name":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":256000},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"display_name":"Mistral Large 3","type":"chat"},{"id":"mistral/mistral-embed","name":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"display_name":"Mistral Embed","type":"chat"},{"id":"mistral/ministral-14b","name":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"display_name":"Ministral 14B","type":"chat"},{"id":"mistral/codestral","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"display_name":"Codestral (latest)","type":"chat"},{"id":"mistral/ministral-8b","name":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.1,"output":0.1},"display_name":"Ministral 8B (latest)","type":"chat"},{"id":"mistral/ministral-3b","name":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":128000},"cost":{"input":0.04,"output":0.04},"display_name":"Ministral 3B (latest)","type":"chat"},{"id":"fish-audio/s2.1-pro","name":"S2.1 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-07-28","last_updated":"2026-07-28","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"S2.1 Pro","type":"chat"},{"id":"fish-audio/drama-3","name":"Drama 3","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Drama 3","type":"chat"},{"id":"fish-audio/s1","name":"S1","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"S1","type":"chat"},{"id":"fish-audio/transcribe-1","name":"Transcribe-1","description":"Speech transcription model for accurate audio-to-text and captioning workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Transcribe-1","type":"chat"},{"id":"fish-audio/s2-pro","name":"S2 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"S2 Pro","type":"chat"},{"id":"morph/morph-v3-fast","name":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":0.8,"output":1.2},"display_name":"Morph v3 Fast","type":"chat"},{"id":"morph/morph-v3-large","name":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.9,"output":1.9},"display_name":"Morph v3 Large","type":"chat"},{"id":"openai/gpt-4.1-mini-fast","name":"GPT-4.1 mini (Fast)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1014808,"output":32768},"cost":{"input":0.7,"output":2.8,"cache_read":0.175},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini (Fast)","type":"chat"},{"id":"openai/o3-fast","name":"o3 (Fast)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":100000,"output":100000},"cost":{"input":3.5,"output":14,"cache_read":0.875},"canonical_model_id":"openai/o3","display_name":"o3 (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4","name":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT 5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT 5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT 5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":112000,"output":16000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-safeguard-120b","display_name":"GPT OSS Safeguard 120B","type":"chat"},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"input":12289,"output":4096},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5 Turbo","type":"chat"},{"id":"openai/gpt-5.2-fast","name":"GPT 5.2 (Fast)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":3.5,"output":28,"cache_read":0.35},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT 5.2 (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-transcribe","name":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":2.5,"output":10},"display_name":"GPT-4o Transcribe","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT 5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":872000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT 5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":6656,"output":1536},"display_name":"text-embedding-3-small","type":"embedding"},{"id":"openai/gpt-5.4-nano","name":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT 5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-realtime-2.1","name":"gpt-realtime-2.1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-09-30","release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"input":96000,"output":32000},"cost":{"input":4,"output":24,"cache_read":0.4},"canonical_model_id":"openai/gpt-realtime-2.1","display_name":"gpt-realtime-2.1","type":"chat"},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2-Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-fast","name":"GPT-4o (Fast)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"cost":{"input":4.25,"output":17,"cache_read":2.125},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o (Fast)","type":"chat"},{"id":"openai/gpt-5.1-codex","name":"GPT-5.1-Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol-fast","name":"GPT-6.1 Sol (Fast)","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.4,"cache_write":10,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.4,"cache_write":10}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol (Fast)","type":"chat"},{"id":"openai/gpt-live-1","name":"GPT-Live 1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"GPT-Live 1","type":"chat"},{"id":"openai/gpt-realtime-1.5","name":"GPT-Realtime-1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":4,"output":16,"cache_read":0.4},"display_name":"GPT-Realtime-1.5","type":"chat"},{"id":"openai/gpt-4.1-nano-fast","name":"GPT-4.1 nano (Fast)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1014808,"output":32768},"cost":{"input":0.2,"output":0.8,"cache_read":0.05},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano (Fast)","type":"chat"},{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"canonical_model_id":"openai/gpt-5-codex","display_name":"GPT-5-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-image-2","name":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2","display_name":"GPT Image 2","type":"image-generation"},{"id":"openai/gpt-5.6-luna-fast","name":"GPT 5.6 Luna (Fast)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":0.8,"output":3.6,"cache_read":0.08,"cache_write":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.8,"output":3.6,"cache_read":0.08,"cache_write":1}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT 5.6 Luna (Fast)","type":"chat"},{"id":"openai/gpt-6-astra-fast","name":"GPT-6 Astra (Fast)","description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":20,"output":100,"cache_read":2,"cache_write":25,"tiers":[{"input":40,"output":150,"cache_read":4,"cache_write":50,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":40,"output":150,"cache_read":4,"cache_write":50}},"canonical_model_id":"openai/gpt-6-astra-fast","display_name":"GPT-6 Astra (Fast)","type":"chat"},{"id":"openai/gpt-5.2-pro","name":"GPT 5.2 ","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"canonical_model_id":"openai/gpt-5.2-pro","display_name":"GPT 5.2 ","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-thinking-fast","name":"GPT 5.1 Thinking (Fast)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2.5,"output":20,"cache_read":0.25},"display_name":"GPT 5.1 Thinking (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":6656,"output":1536},"display_name":"text-embedding-ada-002","type":"embedding"},{"id":"openai/gpt-5.3-codex","name":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT 5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/whisper-1","name":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2022-09-21","last_updated":"2022-09-21","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Whisper","type":"chat"},{"id":"openai/gpt-5.3-codex-fast","name":"GPT 5.3 Codex (Fast)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":3.5,"output":28,"cache_read":0.35},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT 5.3 Codex (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5-fast","name":"GPT 5.5 (Fast)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":872000,"output":128000},"cost":{"input":12.5,"output":75,"cache_read":1.25},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT 5.5 (Fast)","type":"chat"},{"id":"openai/gpt-image-2.5-flare","name":"GPT Image 2.5 Flare","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2.5-flare","display_name":"GPT Image 2.5 Flare","type":"image-generation"},{"id":"openai/gpt-5.4-fast","name":"GPT 5.4 (Fast)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT 5.4 (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol-fast","name":"GPT 5.6 Sol (Fast)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":8,"output":40,"cache_read":0.8,"cache_write":10,"tiers":[{"input":16,"output":60,"cache_read":1.6,"cache_write":20,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":16,"output":60,"cache_read":1.6,"cache_write":20}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT 5.6 Sol (Fast)","type":"chat"},{"id":"openai/o4-mini-fast","name":"o4-mini (Fast)","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":100000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-pro","name":"GPT-5 pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":128000,"output":272000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-5.1-thinking","name":"GPT 5.1 Thinking","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-11-12","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT 5.1 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":6656,"output":1536},"display_name":"text-embedding-3-large","type":"embedding"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-mini-fast","name":"GPT 5.4 Mini (Fast)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.5,"output":9,"cache_read":0.15},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT 5.4 Mini (Fast)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-realtime-mini","name":"GPT-Realtime mini","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-10","last_updated":"2025-10-10","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.6,"output":2.4,"cache_read":0.06},"display_name":"GPT-Realtime mini","type":"chat"},{"id":"openai/gpt-5-mini-fast","name":"GPT-5 mini (Fast)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.45,"output":3.6,"cache_read":0.045},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 mini (Fast)","type":"chat"},{"id":"openai/o3-pro","name":"o3 Pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":100000,"output":100000},"cost":{"input":20,"output":80},"canonical_model_id":"openai/o3-pro","display_name":"o3 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":122880,"output":8192},"cost":{"input":0.03,"output":0.14},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":112000,"output":16000},"cost":{"input":0.07,"output":0.2},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"gpt-oss-safeguard-20b","type":"chat"},{"id":"openai/gpt-image-2.5-sunburst","name":"GPT Image 2.5 Sunburst","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-09-08","last_updated":"2026-09-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2.5-sunburst","display_name":"GPT Image 2.5 Sunburst","type":"image-generation"},{"id":"openai/gpt-5.6-terra-fast","name":"GPT 5.6 Terra (Fast)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":24,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":36,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":36,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT 5.6 Terra (Fast)","type":"chat"},{"id":"openai/gpt-image-1","name":"GPT Image 1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":40,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-1","display_name":"GPT Image 1","type":"image-generation"},{"id":"openai/gpt-5.4-mini","name":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT 5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT 5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-max","name":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT 5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":872000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT 5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol-fast","name":"GPT-6 Sol (Fast)","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol (Fast)","type":"chat"},{"id":"openai/tts-1","name":"TTS-1","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"TTS-1","type":"chat"},{"id":"openai/gpt-6-luna-fast","name":"GPT-6 Luna (Fast)","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.5,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":0.4,"output":1.5,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna (Fast)","type":"chat"},{"id":"openai/gpt-5-fast","name":"GPT-5 (Fast)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2.5,"output":20,"cache_read":0.25},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5 (Fast)","type":"chat"},{"id":"openai/gpt-realtime-2","name":"gpt-realtime-2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":4,"output":24,"cache_read":0.4},"display_name":"gpt-realtime-2","type":"chat"},{"id":"openai/gpt-4.1-fast","name":"GPT-4.1 (Fast)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1014808,"output":32768},"cost":{"input":3.5,"output":14,"cache_read":0.875},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1 (Fast)","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-image-1-mini","name":"GPT Image 1 Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":2,"output":8,"cache_read":0.2},"display_name":"GPT Image 1 Mini","type":"image-generation"},{"id":"openai/gpt-4o-mini-transcribe","name":"GPT-4o mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"o-mini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":1.25,"output":5},"display_name":"GPT-4o mini Transcribe","type":"chat"},{"id":"openai/gpt-image-1.5","name":"GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":32,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-1.5","display_name":"GPT Image 1.5","type":"image-generation"},{"id":"openai/gpt-5.6-terra","name":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT 5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.5,"cache_read":0.1},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT 5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini-fast","name":"GPT-4o mini (Fast)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"cost":{"input":0.25,"output":1,"cache_read":0.125},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini (Fast)","type":"chat"},{"id":"openai/gpt-realtime-whisper","name":"gpt-realtime-whisper","description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"canonical_model_id":"openai/gpt-realtime-whisper","display_name":"gpt-realtime-whisper","type":"chat"},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272001}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"openai/tts-1-hd","name":"TTS-1 HD","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"TTS-1 HD","type":"chat"},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":2.5,"output":20,"cache_read":0.25},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.625,"output":5,"cache_read":0.0625},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":14,"cache_read":0.875},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":1,"output":4,"cache_read":0.25},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"experimental":{"modes":{"fast":{"cost":{"input":0.7,"output":2.8,"cache_read":0.175},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":14,"cache_read":0.875},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"experimental":{"modes":{"fast":{"cost":{"input":0.25,"output":1,"cache_read":0.125},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"display_name":"GPT-4o mini","type":"chat"},{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"flex":{"cost":{"input":0.025,"output":0.2,"cache_read":0.0025},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","experimental":{"modes":{"fast":{"cost":{"input":0.2,"output":0.8,"cache_read":0.05},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"display_name":"GPT-4.1 nano","type":"chat"},{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","experimental":{"modes":{"fast":{"cost":{"input":2,"output":8,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.55,"output":2.2,"cache_read":0.138},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":0.45,"output":3.6,"cache_read":0.045},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.125,"output":1,"cache_read":0.0125},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"experimental":{"modes":{"fast":{"cost":{"input":4.25,"output":17,"cache_read":2.125},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":10,"cache_read":1.25},"display_name":"GPT-4o","type":"chat"},{"id":"microsoft/mai-voice-2.1-flash","name":"MAI-Voice-2.1-Flash","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"MAI-Voice-2.1-Flash","type":"chat"},{"id":"microsoft/mai-image-2.6","name":"MAI-Image-2.6","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":38},"display_name":"MAI-Image-2.6","type":"image-generation"},{"id":"microsoft/mai-transcribe-2-streaming","name":"MAI-Transcribe-2-Streaming","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"MAI-Transcribe-2-Streaming","type":"chat"},{"id":"microsoft/mai-transcribe-2","name":"MAI-Transcribe 2","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-03","last_updated":"2026-09-03","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"MAI-Transcribe 2","type":"chat"},{"id":"microsoft/mai-image-2.6-flash","name":"MAI-Image-2.6-Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":1.75,"output":19},"display_name":"MAI-Image-2.6-Flash","type":"image-generation"},{"id":"microsoft/mai-voice-2","name":"MAI-Voice-2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"MAI-Voice-2","type":"chat"},{"id":"microsoft/mai-voice-2.1","name":"MAI-Voice-2.1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"MAI-Voice-2.1","type":"chat"},{"id":"microsoft/mai-voice-2-flash","name":"MAI-Voice-2-Flash","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mai","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"MAI-Voice-2-Flash","type":"chat"}]},"zai-coding-plan":{"id":"zai-coding-plan","api":"https://api.z.ai/api/coding/paas/v4","name":"Z.AI Coding Plan","doc":"https://docs.z.ai/devpack/overview","display_name":"Z.AI Coding Plan","models":[{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3-highspeed","name":"GLM-5.3 Highspeed","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2-highspeed","name":"GLM-5.2 Highspeed","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5-turbo","name":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"ebcloud":{"id":"ebcloud","api":"https://maas-api.ebcloud.com/v1","name":"EBCloud","doc":"https://docs.ebtech.com/ai/model-api.html","display_name":"EBCloud","models":[{"id":"Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.9286,"output":3.8571},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.8571,"output":3.4286},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.143,"output":0.2857},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.4286,"output":0.8571},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"greenpt":{"id":"greenpt","api":"https://api.greenpt.ai/v1","name":"GreenPT","doc":"https://docs.greenpt.ai","display_name":"GreenPT","models":[{"id":"glm-5.2-honey-ultra","name":"GLM-5.2 Honey Ultra","description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Honey Ultra","type":"chat"},{"id":"glm-5.2-ponytail-lite","name":"GLM-5.2 Ponytail Lite","description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Ponytail Lite","type":"chat"},{"id":"gemma-3-27b-it","name":"Gemma 3 27B","description":"Google Gemma 3 multimodal model for chat, reasoning, and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":40000,"output":8192},"cost":{"input":0.342,"output":0.684},"display_name":"Gemma 3 27B","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.127754,"output":0.511016,"cache_read":0.0255508},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.1596,"output":0.399,"cache_read":0.0456},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen3 235B MoE instruct model for long-context multilingual chat and reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":1.026,"output":3.078},"display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3.762,"output":18.81,"cache_read":0.9405},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.255552,"output":1.27776,"cache_read":0.0127776},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.1938,"output":1.129,"cache_read":0.0627},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.7524,"output":4.275,"cache_read":0.2508},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"green-s","name":"Green S","description":"GreenPT speech-to-text model for pre-recorded and live transcription","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.00437,"output":0},"display_name":"Green S","type":"chat"},{"id":"green-l","name":"Green L","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.285,"output":0.912},"canonical_model_id":"mistral/mistral-small-2506","display_name":"Green L","type":"chat"},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.285,"output":1.083},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"output":16384},"cost":{"input":1.254,"output":1.254},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"gemma4","name":"gemma4","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.57,"output":1.71},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"gemma4","type":"chat"},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.342,"output":2.052},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"pixtral-12b-2409","name":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-01","last_updated":"2024-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.285,"output":0.285},"canonical_model_id":"mistral/pixtral-12b","display_name":"Pixtral 12B","type":"chat"},{"id":"glm-5.2-honey","name":"GLM-5.2 Honey","description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Honey","type":"chat"},{"id":"holo2-30b-a3b","name":"Holo2 30B A3B","description":"H Company Holo2 vision model for GUI navigation and computer-use agents","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11","last_updated":"2025-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":22016,"output":16384},"cost":{"input":0.399,"output":0.969},"display_name":"Holo2 30B A3B","type":"chat"},{"id":"green-r-raw","name":"Green R Raw","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.399,"output":1.083},"canonical_model_id":"openai/gpt-oss-120b","display_name":"Green R Raw","type":"chat"},{"id":"green-s-pro","name":"Green S Pro","description":"GreenPT advanced speech-to-text model with multilingual transcription support","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-02","last_updated":"2025-02","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.00437,"output":0},"display_name":"Green S Pro","type":"chat"},{"id":"devstral-2-123b-instruct-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":16384},"cost":{"input":0.57,"output":2.736},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"mistral-medium-3.5-128b","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":2.052,"output":10.26},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.798,"output":4.959},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"voxtral-small-24b-2507","name":"Voxtral Small 24B","description":"Mistral Voxtral audio-understanding model for speech and transcription tasks","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.228,"output":0.513},"display_name":"Voxtral Small 24B","type":"chat"},{"id":"green-l-raw","name":"Green L Raw","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.285,"output":0.912},"canonical_model_id":"mistral/mistral-small-2506","display_name":"Green L Raw","type":"chat"},{"id":"glm-5.2-ponytail-ultra","name":"GLM-5.2 Ponytail Ultra","description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Ponytail Ultra","type":"chat"},{"id":"green-r","name":"Green R","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.399,"output":1.083},"canonical_model_id":"openai/gpt-oss-120b","display_name":"Green R","type":"chat"},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"status":"deprecated","cost":{"input":1.756,"output":5.518},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-small-3.2-24b-instruct-2506","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.228,"output":0.456},"canonical_model_id":"mistral/mistral-small-2506","display_name":"Mistral Small 3.2","type":"chat"},{"id":"glm-5.2-caveman","name":"GLM-5.2 Caveman","description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Caveman","type":"chat"},{"id":"kimi-k2.6-fast","name":"Kimi K2.6 Fast","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":1.655,"output":8.778},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 Fast","type":"chat"},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.228,"output":0.798},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.27754,"output":5.11016,"cache_read":0.319385},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2-caveman-ultra","name":"GLM-5.2 Caveman Ultra","description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Caveman Ultra","type":"chat"},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.9006,"output":4.389,"cache_read":0.1881},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2-ponytail","name":"GLM-5.2 Ponytail","description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Ponytail","type":"chat"},{"id":"glm-5.2-honey-lite","name":"GLM-5.2 Honey Lite","description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Honey Lite","type":"chat"},{"id":"glm-5.2-caveman-lite","name":"GLM-5.2 Caveman Lite","description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 Caveman Lite","type":"chat"}]},"mixlayer":{"id":"mixlayer","api":"https://models.mixlayer.ai/v1","name":"Mixlayer","doc":"https://docs.mixlayer.com","display_name":"Mixlayer","models":[{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":2.4},"display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":3.2},"display_name":"Qwen3.5 122B A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.4},"display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1.3},"display_name":"Qwen3.5 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3.6},"display_name":"Qwen3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"hyper":{"id":"hyper","api":"https://hyper.charm.land/v1","name":"Charm Hyper","doc":"https://hyper.charm.land","display_name":"Charm Hyper","models":[{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-28","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.5,"output":7.5,"cache_read":0.5},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.5,"output":3,"cache_read":0.1},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.16332,"output":0.5444,"cache_read":0.031575},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max-preview","display_name":"Qwen3.8 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16000},"cost":{"input":3.2664,"output":16.332,"cache_read":0.32664},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":0.33,"output":1.31,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.7-flash","name":"Qwen3.7 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-27","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991808,"output":64000},"cost":{"input":0.2,"output":0.8,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":26214},"cost":{"input":0.6,"output":2.5,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":25600},"cost":{"input":0.098,"output":0.334,"cache_read":0.049},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-05","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":6553},"cost":{"input":0.484,"output":1.852,"cache_read":0.242},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"cost":{"input":1.437216,"output":4.311648,"cache_read":0.047907},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-15","last_updated":"2026-09-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":1.0888,"output":4.40964,"cache_read":0.185096},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":512000},"cost":{"input":0.32664,"output":1.30656,"cache_read":0.064239},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"prism","name":"Prism","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":true,"release_date":"1970-01-01","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":16000},"cost":{"input":3.2664,"output":16.332,"cache_read":0.32664},"display_name":"Prism","type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":1.52432,"output":4.79072,"cache_read":0.152432},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-13","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":13107},"cost":{"input":0.178,"output":0.68,"cache_read":0.089},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.52432,"output":4.79072,"cache_read":0.283088},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-07-03","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16000},"cost":{"input":1.03436,"output":4.3552,"cache_read":0.206872},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-15","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.2,"output":4.8,"cache_read":0.24},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"jalapeno":{"id":"jalapeno","api":"https://api.jalapeno-cloud.ai/v1","name":"Jalapeno Cloud","doc":"https://www.jalapeno-cloud.ai/docs/","display_name":"Jalapeno Cloud","models":[{"id":"Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":129024,"output":32768},"cost":{"input":0.3,"output":1.5},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":512000},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Qwen3-Next-80B-A3B-Instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":129024,"output":32768},"cost":{"input":0.15,"output":1.5},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct","type":"chat"},{"id":"GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.38,"output":4.4},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"input":192000,"output":128000},"cost":{"input":0.14,"output":0.58},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Qwen3-VL-235B-A22B-Thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.98,"output":3.95},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-thinking","display_name":"Qwen3 VL 235B A22B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.5},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-thinking","display_name":"Qwen3-Next 80B-A3B (Thinking)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.6,"output":3.38},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"Qwen3.5-35B-A3B","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen3.5-397B-A17B","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":271360,"output":262144},"cost":{"input":0.95,"output":4},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Kimi-K2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":180224},"cost":{"input":0.6,"output":3},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"dinference":{"id":"dinference","api":"https://api.dinference.com/v1","name":"DInference","doc":"https://dinference.com","display_name":"DInference","models":[{"id":"glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.75,"output":2.4},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.22,"output":0.88},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.45,"output":1.65},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.25,"output":3.89},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.25,"output":3.89},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"release_date":"2025-08","last_updated":"2025-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.0675,"output":0.27},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"neosmith":{"id":"neosmith","api":"https://router.neosmith.ai/v1","name":"NeoSmith","doc":"https://neosmith.ai/docs","display_name":"NeoSmith","models":[{"id":"neosmith.neolite","name":"NeoSmith NeoLite","description":"Sealed single-model budget tier. 512K context, text and images, tool use, and no escalation of any kind.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-20","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":64000},"cost":{"input":0.6,"output":2.4,"cache_read":0.08,"cache_write":0},"display_name":"NeoSmith NeoLite","type":"chat"},{"id":"neosmith.intelligent-maestro","name":"NeoSmith Maestro","description":"Highest-accuracy coding tier. Hard, self-contained problems run NeoSmith's premium multi-model solver; everything else gets the strongest intelligence tier.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.4,"output":12,"cache_read":0.35,"cache_write":0},"display_name":"NeoSmith Maestro","type":"chat"},{"id":"neosmith.intelligent-pro","name":"NeoSmith Pro","description":"Default production tier. Intelligent NeoSmith routing with a Claude Opus ceiling on escalation.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-26","last_updated":"2026-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.81,"output":8.39,"cache_read":0.3,"cache_write":0},"display_name":"NeoSmith Pro","type":"chat"},{"id":"neosmith.intelligent-basic","name":"NeoSmith Basic","description":"Cost-capped tier. Intelligent routing with a Claude Sonnet ceiling — Opus is never invoked.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-26","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.17,"output":4.37,"cache_read":0.22,"cache_write":0},"display_name":"NeoSmith Basic","type":"chat"}]},"fireworks-ai":{"id":"fireworks-ai","api":"https://api.fireworks.ai/inference/v1/","name":"Fireworks AI","doc":"https://fireworks.ai/docs/","display_name":"Fireworks AI","models":[{"id":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat"},{"id":"accounts/fireworks/models/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"experimental":{"modes":{"priority":{"cost":{"input":3.75,"output":18.75,"cache_read":0.375},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"accounts/fireworks/models/qwen3p8-2p4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/models/ember-1","name":"Ember-1","description":"Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"display_name":"Ember-1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/models/deepseek-v4p1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"experimental":{"modes":{"priority":{"cost":{"input":0.375,"output":1.5,"cache_read":0.0075},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/models/glm-5p3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-09-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048573,"output":262144},"experimental":{"modes":{"priority":{"cost":{"input":1.75,"output":5.5,"cache_read":0.325},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"experimental":{"modes":{"priority":{"cost":{"input":0.0625,"output":0.25,"cache_read":0.0125},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B A3B","type":"chat"},{"id":"accounts/fireworks/models/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"accounts/fireworks/models/minimax-m3","name":"MiniMax-M3","description":"Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":512000},"experimental":{"modes":{"priority":{"cost":{"input":0.45,"output":1.8,"cache_read":0.09},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"accounts/fireworks/models/glm-5p3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-09-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048573,"output":131072},"experimental":{"modes":{"priority":{"cost":{"input":0.1875,"output":0.625,"cache_read":0.0375},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/models/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"experimental":{"modes":{"priority":{"cost":{"input":0.18,"output":0.72,"cache_read":0.018},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"accounts/fireworks/models/muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"accounts/fireworks/models/qwen3p8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"experimental":{"modes":{"priority":{"cost":{"input":3,"output":9,"cache_read":0.375},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat"},{"id":"accounts/fireworks/routers/minimax-latest","name":"MiniMax Latest","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-12","last_updated":"2026-09-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":512000},"experimental":{"modes":{"priority":{"cost":{"input":0.45,"output":1.8,"cache_read":0.09},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/glm-flash-latest","name":"GLM Flash Latest (GLM 5.3 Flash)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048573,"output":131072},"experimental":{"modes":{"priority":{"cost":{"input":0.1875,"output":0.625,"cache_read":0.0375},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM Flash Latest (GLM 5.3 Flash)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/glm-fast-latest","name":"GLM 5.3 Fast (Latest)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-09-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048572,"output":262144},"cost":{"input":2.1,"output":6.6,"cache_read":0.39},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 Fast (Latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/kimi-k3-fast","name":"Kimi K3 Fast","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/glm-5p3-fast","name":"GLM 5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-09-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048572,"output":262144},"cost":{"input":2.1,"output":6.6,"cache_read":0.39},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/kimi-fast-latest","name":"Kimi Fast Latest","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi Fast Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/qwen-max-latest","name":"Qwen Max Latest (Qwen3.8 Max)","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-09-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"experimental":{"modes":{"priority":{"cost":{"input":3,"output":9,"cache_read":0.375},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen Max Latest (Qwen3.8 Max)","type":"chat"},{"id":"accounts/fireworks/routers/kimi-latest","name":"Kimi Latest","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"experimental":{"modes":{"priority":{"cost":{"input":3.75,"output":18.75,"cache_read":0.375},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/deepseek-flash-latest","name":"DeepSeek Flash Latest","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"experimental":{"modes":{"priority":{"cost":{"input":0.375,"output":1.5,"cache_read":0.0075},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek Flash Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"accounts/fireworks/routers/glm-latest","name":"GLM Latest","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-09-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048573,"output":262144},"experimental":{"modes":{"priority":{"cost":{"input":1.75,"output":5.5,"cache_read":0.325},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"stepfun-ai":{"id":"stepfun-ai","api":"https://api.stepfun.ai/v1","name":"StepFun (Global)","doc":"https://platform.stepfun.ai/docs/en/overview/concept","display_name":"StepFun (Global)","models":[{"id":"step-5-preview","name":"Step 5 Preview","description":"StepFun frontier model for large-scale agent applications, coding, and knowledge work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":1,"output":2.7,"cache_read":0.05},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","metadata":{"source":"public-provider-conf-template","lifecycle":"preview","notes":["Official maximum input and output are both 1M tokens and max_tokens defaults to INF; 384000 is recorded as a conservative default output ceiling.","Output tokens include both the reasoning process and the final answer; cache-miss input billing includes writing new content to the cache."]},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["low","medium","high"],"mode":"effort","effort":"medium"}},"temperature":true,"type":"chat","vision":true},{"id":"step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-06-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.185,"output":1.11,"cache_read":0.037},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"display_name":"Step 3.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"stepaudio-2.5-asr","name":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"step","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-24","last_updated":"2026-07-02","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"StepAudio 2.5 ASR","type":"chat"},{"id":"stepaudio-2.5-tts","name":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"StepAudio 2.5 TTS","type":"chat"},{"id":"step-2-16k","name":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":5.21,"output":16.44,"cache_read":1.04},"display_name":"Step 2 (16K)","type":"chat"},{"id":"step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"display_name":"Step 3.5 Flash 2603","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-tts-2","name":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-03-01","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Step TTS 2","type":"chat"},{"id":"step-1-32k","name":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":2.05,"output":9.59,"cache_read":0.41},"display_name":"Step 1 (32K)","type":"chat"}]},"fastrouter":{"id":"fastrouter","api":"https://go.fastrouter.ai/api/v1","name":"FastRouter","doc":"https://fastrouter.ai/models","display_name":"FastRouter","models":[{"id":"anthropic/claude-opus-4.1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"z-ai/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.95,"output":3.15},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.05,"output":3.5},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"sarvam/sarvam-30b","name":"Sarvam 30B","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","family":"sarvam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-18","last_updated":"2026-02-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.02,"output":0.1},"canonical_model_id":"sarvam/sarvam-30b","display_name":"Sarvam 30B","type":"chat"},{"id":"sarvam/sarvam-105b","name":"Sarvam 105B","description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.04,"output":0.16},"canonical_model_id":"sarvam/sarvam-105b","display_name":"Sarvam 105B","type":"chat"},{"id":"x-ai/grok-4","name":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.75,"cache_write":15},"display_name":"Grok 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bytedance/seedance-2","name":"Seedance 2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":4096,"output":8192},"display_name":"Seedance 2","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.38},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image-preview","display_name":"Nano Banana 2 Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/veo3.1","name":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":400000,"output":8192},"display_name":"Veo 3.1","type":"chat"},{"id":"google/imagen-4.0-ultra","name":"Imagen 4 Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Imagen 4 Ultra","type":"chat"},{"id":"google/veo3.1-lite","name":"Veo 3.1 Lite","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":400000,"output":8192},"display_name":"Veo 3.1 Lite","type":"chat"},{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro Preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12},"canonical_model_id":"google/gemini-3-pro-image-preview","display_name":"Nano Banana Pro Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.31},"display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/veo3.1-fast","name":"Veo 3.1 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":400000,"output":8192},"display_name":"Veo 3.1 Fast","type":"chat"},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.0375},"display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/imagen-4.0-fast","name":"Imagen 4 Fast","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":8192},"display_name":"Imagen 4 Fast","type":"chat"},{"id":"deepseek-ai/deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-01-23","last_updated":"2025-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.14},"display_name":"DeepSeek R1 Distill Llama 70B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.75,"output":3.5},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2","name":"Kimi K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.55,"output":2.2},"display_name":"Kimi K2","type":"chat"},{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"wanx/wan-v2-6","name":"Wan 2.6","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":true,"limit":{"context":400000,"output":8192},"display_name":"Wan 2.6","type":"chat"},{"id":"qwen/qwen3-coder","name":"Qwen3 Coder","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":0.3,"output":1.2},"display_name":"Qwen3 Coder","type":"chat"},{"id":"leonardo-ai/lucid-realism","name":"Lucid Realism","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"lucid","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":4096,"output":8192},"display_name":"Lucid Realism","type":"chat"},{"id":"leonardo-ai/lucid-origin","name":"Lucid Origin","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"lucid","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":4096,"output":8192},"display_name":"Lucid Origin","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-realtime-1.5","name":"GPT Realtime 1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","audio","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32000,"output":4096},"cost":{"input":4,"output":16},"display_name":"GPT Realtime 1.5","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-image-2","name":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"GPT Image 2","type":"image-generation"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.05,"output":0.2},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"orcarouter":{"id":"orcarouter","api":"https://api.orcarouter.ai/v1","name":"OrcaRouter","doc":"https://docs.orcarouter.ai","display_name":"OrcaRouter","models":[{"id":"grok/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":10},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.147,"output":0.295,"cache_read":0.02},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.147,"output":0.295,"cache_read":0.02},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.147,"output":0.295,"cache_read":0.02},"canonical_model_id":"deepseek/deepseek-chat","display_name":"DeepSeek Chat","type":"chat"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.442,"output":0.884,"cache_read":0.06},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v4-flash-free","name":"DeepSeek V4 Flash (free)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (free)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.147,"output":0.295,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-reasoner","display_name":"DeepSeek Reasoner","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.442,"output":0.884,"cache_read":0.06},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.147,"output":0.295,"cache_read":0.02},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"tencent/hy3-free","name":"Hy3 (free)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"tencent/hy3","display_name":"Hy3 (free)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0.18,"output":0.59,"cache_read":0.059},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.075,"output":0.25},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.3-flash-free","name":"GLM-5.3-Flash (free)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash (free)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5-Air","type":"chat"},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.26,"output":3.96,"cache_read":0.234},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.1},"canonical_model_id":"google/gemini-flash-latest","display_name":"Gemini Flash Latest","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.38,"cache_read":0.02},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-flash-lite-latest","display_name":"Gemini Flash-Lite Latest","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-robotics-er-1.6-preview","name":"Gemini Robotics-ER 1.6 Preview","description":"Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":1,"output":5},"canonical_model_id":"google/gemini-robotics-er-1.6-preview","display_name":"Gemini Robotics-ER 1.6 Preview","type":"chat"},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.33,"cache_read":0.0075},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333,"input_audio":3},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3.3,"output":16.5,"cache_read":0.33},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3,"cache_read":0.1,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"orcarouter/fusion-mini","name":"OrcaRouter Fusion Mini","description":"Leaner two-model Fusion panel that runs Claude Opus 4.8 and GPT-5.5 in parallel on hard requests, then has a Claude Opus 4.8 judge return the strongest single answer verbatim. Easy requests fall through to a cheaper default and bill as one call.","family":"model-router","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"display_name":"OrcaRouter Fusion Mini","type":"chat"},{"id":"orcarouter/free","name":"OrcaRouter Free","description":"Built-in router over the free tier that scores each request's difficulty and sends light work to the smaller free model and harder work to the stronger one. Priced at zero and never falls back to a paid model.","family":"auto","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":0,"output":0},"display_name":"OrcaRouter Free","type":"chat"},{"id":"orcarouter/fusion","name":"OrcaRouter Fusion","description":"Curated fan-out router that runs Claude Opus 4.8, GPT-5.5 and Gemini 3.1 Pro in parallel on hard requests, then has a Claude Opus 4.8 judge return the strongest single answer verbatim. Easy requests fall through to a cheaper default and bill as one call.","family":"model-router","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"display_name":"OrcaRouter Fusion","type":"chat"},{"id":"orcarouter/fusion-flash","name":"OrcaRouter Fusion Flash","description":"Budget Fusion panel that runs Gemini 3.5 Flash, MiniMax M2.7 and GLM 5.1 in parallel on hard requests, then has a Claude Opus 4.8 judge return the strongest single answer verbatim. Cost-sensitive fan-out over a 200K window.","family":"model-router","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"display_name":"OrcaRouter Fusion Flash","type":"chat"},{"id":"orcarouter/auto","name":"OrcaRouter Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2026-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"display_name":"OrcaRouter Auto","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5-highspeed","display_name":"MiniMax-M2.5-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":1.6},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25,"cache_write":1.563},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.33,"output":2.4},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":40960},"cost":{"input":0.4,"output":4},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-thinking","display_name":"Qwen3 VL 235B A22B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.086,"output":0.688},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.115,"output":0.688,"reasoning":2.4},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991808,"output":131072},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.359,"output":1.434},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.115,"output":0.917},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.057,"output":0.459},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.172,"output":1.032},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.35,"output":1.42,"cache_read":0.071},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5,"cache_read":0},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5-turbo","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":100000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":5,"output":15},"canonical_model_id":"openai/gpt-4o-2024-05-13","display_name":"GPT-4o (2024-05-13)","type":"chat"},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"canonical_model_id":"openai/gpt-5.2-pro","display_name":"GPT-5.2 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"canonical_model_id":"openai/gpt-4","display_name":"GPT-4","type":"chat"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-chat-latest","name":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-chat-latest","display_name":"GPT-5.2 Chat","type":"chat"},{"id":"openai/gpt-5.1-chat-latest","name":"GPT-5.1 Chat","description":"Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-chat-latest","display_name":"GPT-5.1 Chat","type":"chat"},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-chat-latest","name":"GPT-5 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":100000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5-chat-latest","display_name":"GPT-5 Chat (latest)","type":"chat"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-08-06","display_name":"GPT-4o (2024-08-06)","type":"chat"},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-11-20","display_name":"GPT-4o (2024-11-20)","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.03,"output":0.17},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"friendli":{"id":"friendli","api":"https://api.friendli.ai/serverless/v1","name":"Friendli","doc":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","display_name":"Friendli","models":[{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":64000},"cost":{"input":0.5,"output":1.5,"cache_read":0.25},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.26,"output":3.96,"cache_read":0.234},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"kimi-code-plan-cn":{"id":"kimi-code-plan-cn","api":"https://api.kimi.com/coding/v1","name":"Kimi For Coding (kimi.com)","doc":"https://www.kimi.com/code/docs/en/kimi-code/models.html","display_name":"Kimi For Coding (kimi.com)","models":[{"id":"kimi-for-coding-highspeed","name":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi For Coding HighSpeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-for-coding","name":"kimi-for-coding","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.8-preview","display_name":"kimi-for-coding","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"k3-256k","name":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3-256K","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"inco":{"id":"inco","api":"https://api.inco.ai/v1","name":"Inco","doc":"https://platform.inco.ai/docs","display_name":"Inco","models":[{"id":"kimi-k3:fast","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":6,"output":30},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3:fast","name":"GLM-5.3 Fast","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2.8,"output":8.8},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash:fast","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash:fast","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.6,"output":2.4},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m3:fast","name":"MiniMax M3 Fast","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.6,"output":2.4},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3 Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"sakana":{"id":"sakana","api":"https://api.sakana.ai/v1","name":"Sakana AI","doc":"https://console.sakana.ai/models","display_name":"Sakana AI","models":[{"id":"fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"provider":{"shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"fugu-ultra-20260615","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"provider":{"shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"sakana-namazu","name":"Sakana Namazu","description":"Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows","family":"sakana-namazu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.15},"canonical_model_id":"sakana/sakana-namazu","display_name":"Sakana Namazu","type":"chat"},{"id":"fugu","name":"Fugu","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"provider":{"shape":"responses"},"canonical_model_id":"sakana/fugu","display_name":"Fugu","type":"chat"}]},"scx-ai":{"id":"scx-ai","api":"https://api.scx.ai/v1","name":"SCX.ai","doc":"https://platform.scx.ai/docs","display_name":"SCX.ai","models":[{"id":"GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.55,"output":1.784,"cache_read":0.111},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":983616,"output":131072},"cost":{"input":1.815,"output":5.4461,"cache_read":0.17,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.48,"output":1.79,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.17,"output":0.55},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"zenifra":{"id":"zenifra","api":"https://ai.zenifra.com/v1","name":"Zenifra","doc":"https://docs.zenifra.com","display_name":"Zenifra","models":[{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"provider":{"shape":"completions"},"cost":{"input":0.19,"output":0.48},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"tokenrouter":{"id":"tokenrouter","api":"https://api.tokenrouter.com/v1","name":"TokenRouter","doc":"https://www.tokenrouter.com/docs/tokenrouter-feature-guide/","display_name":"TokenRouter","models":[{"id":"z-ai/glm-5.3-free","name":"GLM-5.3 (free)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (free)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"google-vertex-anthropic":{"id":"google-vertex-anthropic","name":"Vertex (Anthropic)","doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude","display_name":"Vertex (Anthropic)","models":[{"id":"claude-opus-4-8@default","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-sonnet-4-5@20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-4-6@default","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-4@20250514","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-20250514","display_name":"Claude Opus 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-5-5@default","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"claude-opus-5-5@default","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-opus-5@default","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat"},{"id":"claude-sonnet-4-6@default","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-haiku-4-5@20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-4-1@20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-4-5@20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-opus-4-7@default","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-fable-5-1@default","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-fable-5@default","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-haiku-5-5@default","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"claude-sonnet-4@20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-5@default","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat"}]},"moonshot-ai":{"id":"moonshot-ai","api":"https://api.moonshot.ai/v1","name":"Moonshot AI","doc":"https://platform.moonshot.ai/docs/api/chat","display_name":"Moonshot AI","models":[{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2.7-code-highspeed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code Highspeed","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}},"type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"Kimi K2.6","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2.7-code","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}},"type":"chat"}]},"ainetcafe":{"id":"ainetcafe","api":"https://microquickjs.com/v1","name":"ainetcafe","doc":"https://ainetcafe.com/k3/guides/","display_name":"ainetcafe","models":[{"id":"Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":2.1,"output":10.5,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"wallaby":{"id":"wallaby","api":"https://api.wallabytoken.com/v1","name":"Wallaby","doc":"https://wallabytoken.com/docs","display_name":"Wallaby","models":[{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2.7,"output":13.5,"cache_read":0.27},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"bee":{"id":"bee","api":"https://api.bee.heossi.com/bee","name":"Bee by HEOSSI","doc":"https://bee.heossi.com/docs/sdks","display_name":"Bee by HEOSSI","models":[{"id":"bee-buzz","name":"Bee Buzz 1.0","description":"Mid-tier production model for tool-using agents, multi-step workflows, and builder/integration work. Bigger context than Comb, deeper planning, faster than Hive on routine tasks.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-09-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":24576},"cost":{"input":2.5,"output":10,"cache_read":0.25,"cache_write":3},"display_name":"Bee Buzz 1.0","type":"chat"},{"id":"bee-swarm","name":"Bee Swarm 1.0","description":"Premium reasoning, multi-model cloud execution, large-document analysis, and high-value technical work. Includes the evolution engine and stronger eval gates by default.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":false,"release_date":"2026-07-10","last_updated":"2026-09-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":25,"output":150,"cache_read":2.5,"cache_write":30},"display_name":"Bee Swarm 1.0","type":"chat"},{"id":"bee-comb","name":"Bee Comb 2.0","description":"Stronger local/workstation AI for coding, architecture, security reasoning, larger RAG, and domain-specific workflows. The default workhorse for engineers and dev teams.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-09-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":1.25,"output":5,"cache_read":0.125,"cache_write":1.5},"display_name":"Bee Comb 2.0","type":"chat"},{"id":"bee-hive","name":"Bee Hive 1.0","description":"Scalable Bee serving with quantum-reasoning routing and multi-base domain-adapter routing for shared knowledge workflows, document intelligence, and lower-cost cloud inference. Domain adapters activate per customer domain after evaluation.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-09-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":5,"output":20,"cache_read":0.5,"cache_write":6},"display_name":"Bee Hive 1.0","type":"chat"},{"id":"bee-brood","name":"Bee Brood 1.0","description":"Production multimodal reasoning for image and video analysis, tool-enabled workflows, and multi-step planning at controlled cost.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-09-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.72},"display_name":"Bee Brood 1.0","type":"chat"},{"id":"bee-cell","name":"Bee Cell 1.0","description":"Fast hosted AI for chat, coding help, document question answering, image understanding, and lightweight technical reasoning.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-09-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.36},"display_name":"Bee Cell 1.0","type":"chat"}]},"scnet-token-plan":{"id":"scnet-token-plan","api":"https://api.scnet.cn/api/llm/v1","name":"SCNet Token Plan","doc":"https://www.scnet.cn/ac/openapi/doc/2.0/moduleapi/plans/token-plan.html","display_name":"SCNet Token Plan","models":[{"id":"DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"GLM-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"Qwen3.8-Flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"Kimi-K2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"ofox":{"id":"ofox","api":"https://api.ofox.ai/v1","name":"Ofox","doc":"https://ofox.ai/docs","display_name":"Ofox","models":[{"id":"bailian/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.022,"output":0.22,"cache_read":0.0043,"cache_write":0.027},"canonical_model_id":"alibaba/qwen-flash","display_name":"Qwen Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bailian/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1131072,"output":131072},"cost":{"input":0.45,"output":3.2,"cache_read":0.05,"cache_write":0.5625},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"bailian/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":2.05,"cache_read":0.29},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.35,"output":1.38,"cache_read":0.069},"canonical_model_id":"alibaba/qwen-max","display_name":"Qwen Max","type":"chat"},{"id":"bailian/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bailian/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.2,"output":1.5},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"bailian/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.4},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.12,"output":0.29,"cache_read":0.023},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.36,"output":1.43,"cache_read":0.072},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.05,"output":0.09,"cache_read":0.0086},"canonical_model_id":"alibaba/qwen-turbo","display_name":"Qwen Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.23,"output":0.58,"cache_read":0.046},"canonical_model_id":"alibaba/qwen-vl-max","display_name":"Qwen-VL Max","type":"chat"},{"id":"bailian/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.29,"output":2.29,"cache_read":0.29},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.31},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.06,"cache_write":0.27},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"bailian/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.8,"output":9,"cache_read":0.2,"cache_write":1},"canonical_model_id":"alibaba/qwen3-coder-plus","display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"bailian/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bailian/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":1.83,"cache_read":0.29},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":2.15,"output":12.86,"cache_read":0.2,"cache_write":1.17},"canonical_model_id":"alibaba/qwen3.6-max-preview","display_name":"Qwen3.6 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.55,"output":3.5,"cache_read":0.55},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bailian/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bailian/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-0423","name":"DeepSeek V4 Flash 0423","description":"Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.19,"output":0.51,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0423","display_name":"DeepSeek V4 Flash 0423","type":"chat"},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"status":"beta","cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro-0423","name":"DeepSeek V4 Pro 0423","description":"DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.15},"canonical_model_id":"deepseek/deepseek-v4-pro-0423","display_name":"DeepSeek V4 Pro 0423","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.29,"output":0.43,"cache_read":0.06},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"z-ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM-5V-Turbo","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.3-flashx","name":"GLM-5.3-FlashX","description":"High-speed GLM-5.3-Flash serving option for coding and agent workflows","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-FlashX","type":"chat"},{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.4,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.072,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flashx","display_name":"GLM-4.7-FlashX","type":"chat"},{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.3},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.20","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":4,"output":12,"cache_read":0.4},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"x-ai/grok-4.1-fast","name":"Grok 4.1 Fast","description":"xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"xai/grok-4.1-fast","display_name":"Grok 4.1 Fast","type":"chat"},{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"volcengine/doubao-seed-2.0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.06,"output":0.56,"cache_read":0.02,"cache_write":0.0024},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed 2.0 Mini","type":"chat"},{"id":"volcengine/doubao-seed-1-6-flash","name":"Seed 1.6 Flash","description":"Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use","family":"seed","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.03,"output":0.22,"cache_read":0.0043},"canonical_model_id":"bytedance-seed/seed-1-6-flash","display_name":"Seed 1.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"volcengine/doubao-seed-2.0-lite","name":"Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.13,"output":0.76,"cache_read":0.03,"cache_write":0.0024},"canonical_model_id":"bytedance-seed/seed-2.0-lite","display_name":"Seed 2.0 Lite","type":"chat"},{"id":"volcengine/doubao-seed-1-8","name":"Seed 1.8","description":"ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-28","last_updated":"2025-12-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.12,"output":0.29,"cache_read":0.023},"canonical_model_id":"bytedance-seed/seed-1-8","display_name":"Seed 1.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"volcengine/doubao-seed-1-6","name":"Seed 1.6","description":"ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks","family":"seed","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.12,"output":0.29,"cache_read":0.023},"canonical_model_id":"bytedance-seed/seed-1-6","display_name":"Seed 1.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"volcengine/doubao-seed-2.0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.67,"output":3.36,"cache_read":0.14,"cache_write":0.0024},"canonical_model_id":"bytedance-seed/seed-2.0-pro","display_name":"Seed 2.0 Pro","type":"chat"},{"id":"volcengine/doubao-seed-1-6-vision","name":"Seed 1.6 Vision","description":"ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.12,"output":1.15,"cache_read":0.023},"canonical_model_id":"bytedance-seed/seed-1-6-vision","display_name":"Seed 1.6 Vision","type":"chat"},{"id":"volcengine/doubao-seed-2.1-turbo","name":"Seed 2.1 Turbo","description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3536,"output":1.7696,"cache_read":0.068,"cache_write":0.0019},"canonical_model_id":"bytedance-seed/seed-2.1-turbo","display_name":"Seed 2.1 Turbo","type":"chat"},{"id":"volcengine/doubao-seed-2.1-pro","name":"Seed 2.1 Pro","description":"Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.7072,"output":3.536,"cache_read":0.1416,"cache_write":0.002},"canonical_model_id":"bytedance-seed/seed-2.1-pro","display_name":"Seed 2.1 Pro","type":"chat"},{"id":"volcengine/doubao-seed-character","name":"Seed Character","description":"ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.177,"output":0.884,"cache_read":0.024,"cache_write":0.0025},"canonical_model_id":"bytedance-seed/seed-character","display_name":"Seed Character","type":"chat"},{"id":"volcengine/doubao-seed-evolving","name":"Seed Evolving","description":"Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.884,"output":4.42,"cache_read":0.177,"cache_write":0.0025},"canonical_model_id":"bytedance-seed/seed-evolving","display_name":"Seed Evolving","type":"chat"},{"id":"volcengine/doubao-seed-2.0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.67,"output":3.36,"cache_read":0.14,"cache_write":0.0024},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"input_audio":1.5},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":4.5},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083,"input_audio":3},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":4.5},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":1,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"input_audio":1.5},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"input_audio":0.75},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":1,"input_audio":0.3},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":2,"output":10,"cache_read":0.1,"input_audio":2},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5-lightning","name":"MiniMax-M2.5 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5-highspeed","display_name":"MiniMax-M2.5 Lightning","type":"chat"},{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax-M2.1 Lightning","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1 Lightning","type":"chat"},{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/m2-her","name":"MiniMax-M2 Her","description":"MiniMax M2 variant tuned for conversational and character-driven agent interactions","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":2048},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2-Her","display_name":"MiniMax-M2 Her","type":"chat"},{"id":"minimax/minimax-m2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax-M2","type":"chat"},{"id":"qwen/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":0.022,"output":0.22,"cache_read":0.0043,"cache_write":0.027},"canonical_model_id":"alibaba/qwen-flash","display_name":"Qwen Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1064000,"output":64000},"cost":{"input":1.71,"output":5.14,"cache_read":0.17,"cache_write":2.14},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1131072,"output":131072},"cost":{"input":0.5,"output":1.71,"cache_read":0.043,"cache_write":0.63},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.29,"output":2.05,"cache_read":0.29},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8000},"cost":{"input":0.35,"output":1.38,"cache_read":0.069},"canonical_model_id":"alibaba/qwen-max","display_name":"Qwen Max","type":"chat"},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.71,"output":5.14,"cache_read":0.17,"cache_write":2.14},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.2,"output":1.5},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.4},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":0.12,"output":0.29,"cache_read":0.023},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.36,"output":1.43,"cache_read":0.072},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.043,"output":0.09,"cache_read":0.0086},"canonical_model_id":"alibaba/qwen-turbo","display_name":"Qwen Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8000},"cost":{"input":0.23,"output":0.58,"cache_read":0.023},"canonical_model_id":"alibaba/qwen-vl-max","display_name":"Qwen-VL Max","type":"chat"},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.29,"output":2.29,"cache_read":0.29},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.31},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":2.5,"cache_read":0.06,"cache_write":0.27},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.8,"output":9,"cache_read":0.2,"cache_write":1},"canonical_model_id":"alibaba/qwen3-coder-plus","display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.11,"output":0.39,"cache_read":0.011,"cache_write":0.14},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.29,"output":1.83,"cache_read":0.29},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":2.15,"output":12.86,"cache_read":0.2,"cache_write":1.17},"canonical_model_id":"alibaba/qwen3.6-max-preview","display_name":"Qwen3.6 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.55,"output":3.5,"cache_read":0.55},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.43,"output":2.57},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1064000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.71,"output":5.14,"cache_read":0.17,"cache_write":2.14},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.18},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32768},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.25,"output":2,"cache_read":0.03},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.18},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.13},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.13},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT-5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.18},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.25,"output":2,"cache_read":0.03},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.13},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"neon":{"id":"neon","api":"${NEON_AI_GATEWAY_BASE_URL}/v1","name":"Neon","doc":"https://neon.com/docs","display_name":"Neon","models":[{"id":"gpt-5-4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5-6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5-3-flash","name":"GLM-5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash","type":"chat"},{"id":"gpt-5-6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-4-maverick","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":8192},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct","type":"chat"},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gemini-3-7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat"},{"id":"gpt-5-4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude Opus 4.1 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5-5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat"},{"id":"gemini-3-1-pro","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat"},{"id":"glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":10000},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct","type":"chat"},{"id":"gemini-3-flash","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":25000},"cost":{"input":0.07,"output":0.3},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"glm-5-3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat"},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"gpt-5-5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4-6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":524288},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat"},{"id":"qwen35-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":25000},"cost":{"input":0.22,"output":2.2},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat"},{"id":"gemini-3-6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat"},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"meta-llama-3-3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"gpt-5-2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-5-3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemma-3-12b","name":"Gemma 3 12B","description":"Google's open-weight Gemma 3 vision-language model for text and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.5},"display_name":"Gemma 3 12B","type":"chat"},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"grok-4-7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2.5,"output":7.5,"cache_read":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"gemini-3-5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat"},{"id":"gemini-3-5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat"},{"id":"gpt-5-1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-6-1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":25000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"meta-llama-3-1-8b-instruct","name":"Llama 3.1 8B Instruct","description":"Meta's compact open-weight Llama 3.1 model for fast, low-cost text generation","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.45},"display_name":"Llama 3.1 8B Instruct","type":"chat"},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"merge-gateway":{"id":"merge-gateway","api":"https://api-gateway.merge.dev/v1/ai-sdk","name":"Merge Gateway","doc":"https://docs.merge.dev/merge-gateway","display_name":"Merge Gateway","models":[{"id":"zai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"zai/glm-5.3-flash","name":"GLM-5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-4.5v","name":"Glm 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"Glm 4.5V","type":"chat"},{"id":"zai/glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.07,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM 4.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":50000}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.05,"output":3.3,"cache_read":0.195},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai/glm-4.7-flashx","name":"GLM-4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7-flashx","display_name":"GLM-4.7 FlashX","type":"chat"},{"id":"zai/glm-5-turbo","name":"GLM-5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5 Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai/glm-4.5-air","name":"GLM-4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5 Air","type":"chat"},{"id":"zai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.7,"output":2.2,"cache_read":0.13},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-3-7-sonnet-20250219","name":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-3-7-sonnet-20250219","display_name":"Claude 3.7 Sonnet","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"anthropic/claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"anthropic/claude-opus-4-20250514","name":"Claude Opus 4 (20250514)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-20250514","display_name":"Claude Opus 4 (20250514)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-1-20250805","name":"Claude Opus 4.1 (20250805)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1 (20250805)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (20251101)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5 (20251101)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":128000}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5 (20250929)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (20250929)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5 (20251001)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (20251001)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-4-20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"cohere/command-r-08-2024","name":"Command R 08-2024","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"cohere/command-r-08-2024","display_name":"Command R 08-2024","type":"chat"},{"id":"cohere/command-a-03-2025","name":"Command A 03-2025","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a-03-2025","display_name":"Command A 03-2025","type":"chat"},{"id":"cohere/command-r7b-12-2024","name":"Command R7B 12-2024","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"canonical_model_id":"cohere/command-r7b-12-2024","display_name":"Command R7B 12-2024","type":"chat"},{"id":"cohere/command-r-plus-08-2024","name":"Command R+ 08-2024","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-r-plus-08-2024","display_name":"Command R+ 08-2024","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.035,"output":0.07,"cache_read":0.007},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-0423","name":"DeepSeek V4 Flash 0423","description":"Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.139,"output":0.278},"canonical_model_id":"deepseek/deepseek-v4-flash-0423","display_name":"DeepSeek V4 Flash 0423","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731-fast","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.28,"output":0.56,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v3","name":"DeepSeek V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":81920},"cost":{"input":0.27,"output":1.1},"canonical_model_id":"deepseek/deepseek-v3","display_name":"DeepSeek V3","type":"chat"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro-0423","name":"DeepSeek V4 Pro 0423","description":"DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.65,"output":3.3},"canonical_model_id":"deepseek/deepseek-v4-pro-0423","display_name":"DeepSeek V4 Pro 0423","type":"chat"},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.56,"output":1.68,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek/deepseek-r1","name":"DeepSeek R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":40960},"cost":{"input":1.35,"output":5.4},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 (0528)","description":"May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":32768},"cost":{"input":1.35,"output":5.4,"cache_read":0.945},"canonical_model_id":"deepseek/deepseek-r1-0528","display_name":"DeepSeek R1 (0528)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.28,"output":0.4,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.1125},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"output":32000},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":262144},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.22,"output":0.5,"cache_read":0.11},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":262144},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":2048},"cost":{"input":0.22,"output":0.22},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama 3.1 8B","type":"chat"},{"id":"meta/llama-3.1-70b-instruct","name":"Llama 3.1 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":2048},"cost":{"input":0.99,"output":0.99},"canonical_model_id":"meta/llama-3.1-70b-instruct","display_name":"Llama 3.1 70B","type":"chat"},{"id":"meta/muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"bytedance/dola-seed-2.0-code-preview","name":"Dola Seed 2.0 Code (preview)","description":"Preview coding model for repository understanding, refactors, and engineering tasks","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"display_name":"Dola Seed 2.0 Code (preview)","type":"chat"},{"id":"bytedance/dola-seed-2.0-code","name":"Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.4,"output":2.4},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code","type":"chat"},{"id":"bytedance/dola-seed-2.0-mini","name":"Seed 2.0 Mini","description":"Low-cost Seed model for general chat, extraction, and lightweight production tasks","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.4},"display_name":"Seed 2.0 Mini","type":"chat"},{"id":"bytedance/dola-seed-2.0-lite","name":"Seed 2.0 Lite","description":"Efficient Seed model for general chat, analysis, and lightweight production tasks","family":"seed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-28","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.25,"output":2},"display_name":"Seed 2.0 Lite","type":"chat"},{"id":"bytedance/dola-seed-2.0-pro","name":"Seed 2.0 Pro","description":"Higher-capability Seed model for complex chat, analysis, and production tasks","family":"seed","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"display_name":"Seed 2.0 Pro","type":"chat"},{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-flash-latest","display_name":"Gemini Flash Latest","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B It","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B It","type":"chat"},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.08,"output":0.45,"cache_read":0.04},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT","type":"chat"},{"id":"google/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3-pro-preview","display_name":"Gemini 3 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-image","name":"Gemini 2.5 Flash Image","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":2.5},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Gemini 2.5 Flash Image","type":"image-generation"},{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-flash-lite-latest","display_name":"Gemini Flash-Lite Latest","type":"chat"},{"id":"google/gemini-embedding-2","name":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.2,"output":0},"canonical_model_id":"google/gemini-embedding-2","display_name":"Gemini Embedding 2","type":"embedding"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.13,"output":0.4},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B","type":"chat"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-flash-image","name":"Gemini 3.1 Flash Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Gemini 3.1 Flash Image","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.09,"output":0.29},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B","type":"chat"},{"id":"google/gemini-2.5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview (10-2025)","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-07","last_updated":"2025-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":1.25,"output":10},"canonical_model_id":"google/gemini-2.5-computer-use-preview-10-2025","display_name":"Gemini 2.5 Computer Use Preview (10-2025)","type":"chat"},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-pro-image","name":"Gemini 3 Pro Image","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":2,"output":12},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Gemini 3 Pro Image","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.04,"output":0.08},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B","type":"chat"},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":4096},"cost":{"input":0.15,"output":0},"canonical_model_id":"google/gemini-embedding-001","display_name":"Gemini Embedding 001","type":"embedding"},{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"writer/palmyra-x4","name":"Palmyra X4","description":"Enterprise language model for writing, analysis, and tool-assisted workflows","family":"palmyra","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-10-09","last_updated":"2024-10-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":2.5,"output":10},"display_name":"Palmyra X4","type":"chat"},{"id":"writer/palmyra-x5","name":"Palmyra X5","description":"Enterprise multimodal model for writing, analysis, and tool-assisted workflows","family":"palmyra","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.6,"output":6},"display_name":"Palmyra X5","type":"chat"},{"id":"xai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20","type":"chat"},{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 Non-Reasoning","type":"chat"},{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"sakana/fugu-max","name":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"sakana/fugu-max","display_name":"Fugu Max","type":"chat"},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"sakana/sakana-namazu","name":"Sakana Namazu","description":"Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows","family":"sakana-namazu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.15},"canonical_model_id":"sakana/sakana-namazu","display_name":"Sakana Namazu","type":"chat"},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.6,"output":2.5},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.05,"output":0.2},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B A3B","type":"chat"},{"id":"nvidia/nemotron-nano-9b-v2","name":"Nemotron Nano 9B","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.06,"output":0.23},"canonical_model_id":"nvidia/nemotron-nano-9b-v2","display_name":"Nemotron Nano 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":128000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 Highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax M2.7 Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5 Highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5-highspeed","display_name":"MiniMax M2.5 Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2","name":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax M2","type":"chat"},{"id":"mistral/codestral-latest","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9},"canonical_model_id":"mistral/codestral-latest","display_name":"Codestral (latest)","type":"chat"},{"id":"mistral/mistral-large-2411","name":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-18","last_updated":"2024-11-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":2,"output":6},"canonical_model_id":"mistral/mistral-large-2411","display_name":"Mistral Large 2.1","type":"chat"},{"id":"mistral/mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-latest","display_name":"Mistral Large (latest)","type":"chat"},{"id":"mistral/mistral-small-latest","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"mistral/mistral-small-latest","display_name":"Mistral Small (latest)","type":"chat"},{"id":"mistral/devstral-medium-latest","name":"Devstral 2 (latest)","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/devstral-medium-latest","display_name":"Devstral 2 (latest)","type":"chat"},{"id":"mistral/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.4,"output":2,"cache_read":0.04},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"mistral/mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.4,"output":2,"cache_read":0.04},"canonical_model_id":"mistral/mistral-medium-2505","display_name":"Mistral Medium 3","type":"chat"},{"id":"mistral/magistral-medium-latest","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2,"output":5},"canonical_model_id":"mistral/magistral-medium-latest","display_name":"Magistral Medium (latest)","type":"chat"},{"id":"mistral/devstral-medium-2507","name":"Devstral Medium","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/devstral-medium-2507","display_name":"Devstral Medium","type":"chat"},{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"mistral/devstral-small-2507","name":"Devstral Small","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/devstral-small-2507","display_name":"Devstral Small","type":"chat"},{"id":"mistral/pixtral-large-latest","name":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2024-11-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":2,"output":6},"canonical_model_id":"mistral/pixtral-large-latest","display_name":"Pixtral Large (latest)","type":"chat"},{"id":"mistral/mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/mistral-medium-latest","display_name":"Mistral Medium (latest)","type":"chat"},{"id":"qwen/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.022,"output":0.216,"cache_read":0.0044,"cache_write":0.0275},"canonical_model_id":"alibaba/qwen-flash","display_name":"Qwen Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.029,"output":0.287,"cache_read":0.0029,"cache_write":0.03625},"canonical_model_id":"alibaba/qwen3.5-flash","display_name":"Qwen3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3-VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.21,"output":1.9,"cache_read":0.105},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3-VL 235B A22B Instruct","type":"chat"},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.825,"output":2.4755,"cache_read":0.165,"cache_write":1.03125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3-VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.287,"output":2.867,"cache_read":0.0574},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-thinking","display_name":"Qwen3-VL 235B A22B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":1010000},"cost":{"input":2.5,"output":6.25,"cache_read":0.5},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.143,"output":1.434,"cache_read":0.0286,"cache_write":0.17875},"canonical_model_id":"alibaba/qwen3-vl-plus","display_name":"Qwen3-VL Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.086,"output":0.688,"cache_read":0.0172},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.0574},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-thinking","display_name":"Qwen3-Next 80B-A3B (Thinking)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.15,"output":0.8,"cache_read":0.075},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.115,"output":0.688,"cache_read":0.0115,"cache_write":0.14375},"canonical_model_id":"alibaba/qwen3.5-plus","display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-32b","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.115,"output":0.287,"cache_read":0.023,"cache_write":0.14375},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.359,"output":1.434,"cache_read":0.0718,"cache_write":0.44875},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.22,"output":1.8},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3 Coder 480B A35B Instruct","type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen3-VL 30B-A3B Instruct","description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.0216},"canonical_model_id":"alibaba/qwen3-vl-30b-a3b-instruct","display_name":"Qwen3-VL 30B-A3B Instruct","type":"chat"},{"id":"qwen/qwen3-vl-flash","name":"Qwen3-VL Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.022,"output":0.215,"cache_read":0.0044,"cache_write":0.0275},"canonical_model_id":"alibaba/qwen3-vl-flash","display_name":"Qwen3-VL Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-235b-a22b","name":"Qwen3 235B A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.287,"output":1.147,"cache_read":0.0574},"canonical_model_id":"alibaba/qwen3-235b-a22b","display_name":"Qwen3 235B A22B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.115,"output":0.917,"cache_read":0.023},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-max-preview","name":"Qwen3 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-05","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.08,"output":4.8},"canonical_model_id":"alibaba/qwen3-max-preview","display_name":"Qwen3 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485,"cache_read":0.0496},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":1.1,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct","type":"chat"},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.165,"output":0.99,"cache_read":0.0165,"cache_write":0.20625},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.144,"output":0.574,"cache_read":0.0288,"cache_write":0.18},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.574,"output":2.294,"cache_read":0.1148,"cache_write":0.7175},"canonical_model_id":"alibaba/qwen3-coder-plus","display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.09,"output":0.13},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":977000,"output":128000},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.057,"output":0.459,"cache_read":0.020357},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.31,"output":7.88},"canonical_model_id":"alibaba/qwen3.6-max-preview","display_name":"Qwen3.6 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.108,"output":1.076,"cache_read":0.0216},"canonical_model_id":"alibaba/qwen3-30b-a3b","display_name":"Qwen3 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.172,"output":1.032,"cache_read":0.0344},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.4126,"output":2.4754},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.276,"output":1.651,"cache_read":0.0276,"cache_write":0.345},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":1.6},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-safeguard-120b","display_name":"GPT OSS Safeguard 120B","type":"chat"},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5 Turbo","type":"chat"},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":5,"output":15},"canonical_model_id":"openai/gpt-4o-2024-05-13","display_name":"GPT-4o (2024-05-13)","type":"chat"},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4 Mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3 Mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"canonical_model_id":"openai/gpt-4","display_name":"GPT-4","type":"chat"},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 Nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 Nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-chat-latest","name":"GPT-5.2 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-chat-latest","display_name":"GPT-5.2 Chat Latest","type":"chat"},{"id":"openai/gpt-5.1-chat-latest","name":"GPT-5.1 Chat Latest","description":"Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations","family":"gpt-codex","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-chat-latest","display_name":"GPT-5.1 Chat Latest","type":"chat"},{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"canonical_model_id":"openai/o1","display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-5-chat-latest","name":"GPT-5 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5-chat-latest","display_name":"GPT-5 Chat Latest","type":"chat"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-08-06","display_name":"GPT-4o (2024-08-06)","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o Mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o Mini","type":"chat"},{"id":"openai/gpt-oss-20b","name":"GPT-OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.04,"output":0.15,"cache_read":0.02},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT-OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0.07,"output":0.2,"cache_read":0,"cache_write":0},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-11-20","display_name":"GPT-4o (2024-11-20)","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 Mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 Mini","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5.3-chat-latest","name":"GPT-5.3 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-chat-latest","display_name":"GPT-5.3 Chat Latest","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT-OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.05,"output":0.25},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT-OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":2.9,"output":14,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshot/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"opper":{"id":"opper","api":"https://api.opper.ai/v3/compat","name":"Opper","doc":"https://opper.ai/models","display_name":"Opper","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.46488,"output":2.44062},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.5811,"output":3},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":2.5,"output":6,"cache_read":0.63},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.07},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.5811,"output":2.3244},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125,"tiers":[{"input":6.6,"output":24.75,"cache_read":0.66,"cache_write":8.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6.6,"output":24.75,"cache_read":0.66,"cache_write":8.25}},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"cost":{"input":3,"output":15},"canonical_model_id":"perplexity/sonar-pro","display_name":"Sonar Pro","type":"chat"},{"id":"grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.11622,"output":0.488124},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.69732,"output":2.78928},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.12,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.24,"tier":{"type":"context","size":524288}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.24}},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.5811,"output":2.44062},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.62708,"output":5.811},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":1,"output":1},"canonical_model_id":"perplexity/sonar","display_name":"Sonar","type":"chat"},{"id":"mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.825,"output":4.125,"cache_read":0.0825},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":1.78812,"output":3.57624},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-chat-latest","display_name":"GPT-5.3 Chat (latest)","type":"chat"},{"id":"sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"canonical_model_id":"perplexity/sonar-reasoning-pro","display_name":"Sonar Reasoning Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":1.1622,"output":4.88124},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.75,"output":4.6488,"cache_read":0.44},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.25,"output":0.66},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"nvidia":{"id":"nvidia","api":"https://integrate.api.nvidia.com/v1","name":"Nvidia","doc":"https://docs.api.nvidia.com/nim/","display_name":"Nvidia","models":[{"id":"baai/bge-m3","name":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bge","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-01-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1024},"cost":{"input":0,"output":0},"display_name":"BGE M3","type":"embedding"},{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"canonical_model_id":"poolside/laguna-xs-2.1","display_name":"Laguna XS 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"abacusai/dracarys-llama-3.1-70b-instruct","name":"dracarys-llama-3.1-70b-instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-09-11","last_updated":"2025-05-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"dracarys-llama-3.1-70b-instruct","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"black-forest-labs/flux_1-schnell","name":"FLUX.1-schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-07","release_date":"2024-08-01","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":77,"input":77,"output":8192},"cost":{"input":0,"output":0},"display_name":"FLUX.1-schnell","type":"chat"},{"id":"black-forest-labs/flux.1-dev","name":"FLUX.1-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-08","release_date":"2024-08-01","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":4096,"output":8192},"cost":{"input":0,"output":0},"display_name":"FLUX.1-dev","type":"chat"},{"id":"black-forest-labs/flux_1-kontext-dev","name":"FLUX.1-Kontext-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text","image"],"output":["image"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0,"output":0},"display_name":"FLUX.1-Kontext-dev","type":"chat"},{"id":"black-forest-labs/flux_2-klein-4b","name":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-06","release_date":"2026-01-14","last_updated":"2026-01-31","modalities":{"input":["image","text"],"output":["image"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0,"output":0},"display_name":"FLUX.2 Klein 4B","type":"chat"},{"id":"meta/llama-guard-4-12b","name":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-04-05","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"display_name":"Llama Guard 4 12B","type":"chat"},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta/esmfold","name":"esmfold","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-03-15","last_updated":"2025-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"esmfold","type":"chat"},{"id":"meta/llama-3.3-70b-instruct","name":"Llama 3.3 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-26","last_updated":"2024-11-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 3.3 70b Instruct","type":"chat"},{"id":"meta/llama-3.2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"Llama-3.2-90B-Vision-Instruct","type":"chat"},{"id":"meta/llama-4-maverick-17b-128e-instruct","name":"Llama 4 Maverick 17b 128e Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-02","release_date":"2025-04-01","last_updated":"2025-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 4 Maverick 17b 128e Instruct","type":"chat"},{"id":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 3.1 8B Instruct","type":"chat"},{"id":"meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11b Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"Llama 3.2 11b Vision Instruct","type":"chat"},{"id":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 3.2 1b Instruct","type":"chat"},{"id":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 3.2 3B Instruct","type":"chat"},{"id":"meta/llama-3.1-70b-instruct","name":"Llama 3.1 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-16","last_updated":"2024-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 3.1 70b Instruct","type":"chat"},{"id":"meta/esm2-650m","name":"esm2-650m","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-08-29","last_updated":"2025-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"esm2-650m","type":"chat"},{"id":"upstage/solar-10.7b-instruct","name":"solar-10.7b-instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-06-05","last_updated":"2025-04-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"solar-10.7b-instruct","type":"chat"},{"id":"bytedance/seed-oss-36b-instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"ByteDance-Seed/Seed-OSS-36B-Instruct","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B A4B IT","description":"Gemma 4 based discrete text diffusion model for fast chat, reasoning, and tool use","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-09","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":250000,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/diffusiongemma-26b-a4b-it","display_name":"DiffusionGemma 26B A4B IT","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma-4-31B-IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0,"output":0},"display_name":"Gemma-4-31B-IT","type":"chat"},{"id":"google/gemma-2-2b-it","name":"Gemma 2 2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-16","last_updated":"2024-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Gemma 2 2b It","type":"chat"},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0},"display_name":"Gemma 3 12B IT","type":"chat"},{"id":"google/gemma-3n-e2b-it","name":"Gemma 3n E2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-06-12","last_updated":"2025-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Gemma 3n E2b It","type":"chat"},{"id":"google/google-paligemma","name":"paligemma","description":"Gemini multimodal model for text, image, audio, video, and document tasks","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-05-14","last_updated":"2024-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"paligemma","type":"chat"},{"id":"google/gemma-3n-e4b-it","name":"Gemma 3n E4b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-06-03","last_updated":"2025-06-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Gemma 3n E4b It","type":"chat"},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0},"display_name":"Gemma 3 4B IT","type":"chat"},{"id":"minimaxai/minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimaxai/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"status":"deprecated","cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"status":"deprecated","cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"stepfun-ai/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-02","last_updated":"2026-02-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Step 3.5 Flash","type":"chat"},{"id":"stepfun-ai/step-3.7-flash","name":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Step 3.7 Flash","type":"chat"},{"id":"mistralai/mistral-nemotron","name":"mistral-nemotron","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-06-11","last_updated":"2025-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/mistral-nemotron","display_name":"mistral-nemotron","type":"chat"},{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-01","last_updated":"2025-04-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0,"output":0},"display_name":"Mistral-7B-Instruct-v0.3","type":"chat"},{"id":"mistralai/mistral-large-3-675b-instruct-2512","name":"Mistral Large 3 675B Instruct 2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Mistral Large 3 675B Instruct 2512","type":"chat"},{"id":"mistralai/magistral-small-2506","name":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0,"output":0},"display_name":"Magistral Small 2506","type":"chat"},{"id":"mistralai/mistral-small-4-119b-2603","name":"mistral-small-4-119b-2603","description":"Efficient Mistral model for fast chat, extraction, and production assistants","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"mistral-small-4-119b-2603","type":"chat"},{"id":"mistralai/mixtral-8x7b-instruct","name":"Mistral: Mixtral 8x7B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2023-12-10","last_updated":"2026-03-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Mistral: Mixtral 8x7B Instruct","type":"chat"},{"id":"mistralai/mistral-medium-3.5-128b","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"mistralai/ministral-14b-instruct-2512","name":"Ministral 3 14B Instruct 2512","description":"Compact Mistral VLM for chat and instruction-based workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Ministral 3 14B Instruct 2512","type":"chat"},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":13108},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Mistral: Mixtral 8x22B Instruct","type":"chat"},{"id":"mistralai/mistral-medium-3-instruct","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0,"output":0},"display_name":"Mistral Medium 3","type":"chat"},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"sarvamai/sarvam-m","name":"sarvam-m","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"sarvam-m","type":"chat"},{"id":"nvidia/nvidia-nemotron-nano-9b-v2","name":"nvidia-nemotron-nano-9b-v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-nano-9b-v2","display_name":"nvidia-nemotron-nano-9b-v2","type":"chat"},{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-04-07","last_updated":"2025-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/llama-3.1-nemotron-ultra-253b","display_name":"Llama 3.1 Nemotron Ultra 253B","type":"chat"},{"id":"nvidia/sparsedrive","name":"sparsedrive","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-03-18","last_updated":"2025-07-20","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"sparsedrive","type":"chat"},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"nemotron-3-nano-30b-a3b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"nemotron-3-nano-30b-a3b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B A3B","type":"chat"},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","name":"llama-nemotron-embed-vl-1b-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"nemotron","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-02-10","last_updated":"2026-02-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/llama-nemotron-embed-vl-1b-v2","display_name":"llama-nemotron-embed-vl-1b-v2","type":"chat"},{"id":"nvidia/nv-embedcode-7b-v1","name":"nv-embedcode-7b-v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-03-17","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"display_name":"nv-embedcode-7b-v1","type":"chat"},{"id":"nvidia/nemotron-voicechat","name":"nemotron-voicechat","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-voicechat","display_name":"nemotron-voicechat","type":"chat"},{"id":"nvidia/bevformer","name":"bevformer","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-03-18","last_updated":"2025-07-20","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"bevformer","type":"chat"},{"id":"nvidia/cosmos-transfer1-7b","name":"cosmos-transfer1-7b","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-13","last_updated":"2025-06-30","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"cosmos-transfer1-7b","type":"chat"},{"id":"nvidia/cosmos-predict1-5b","name":"cosmos-predict1-5b","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-03-18","last_updated":"2025-03-18","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"cosmos-predict1-5b","type":"chat"},{"id":"nvidia/llama-3.1-nemotron-nano-vl-8b-v1","name":"Llama 3.1 Nemotron Nano VL 8B v1","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-04-10","last_updated":"2025-04-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 3.1 Nemotron Nano VL 8B v1","type":"chat"},{"id":"nvidia/studiovoice","name":"studiovoice","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-10-03","last_updated":"2025-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"studiovoice","type":"chat"},{"id":"nvidia/nemotron-content-safety-reasoning-4b","name":"nemotron-content-safety-reasoning-4b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":false,"release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-content-safety-reasoning-4b","display_name":"nemotron-content-safety-reasoning-4b","type":"chat"},{"id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","name":"llama-3.1-nemotron-safety-guard-8b-v3","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","display_name":"llama-3.1-nemotron-safety-guard-8b-v3","type":"chat"},{"id":"nvidia/nv-embed-v1","name":"nv-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-06-07","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"display_name":"nv-embed-v1","type":"chat"},{"id":"nvidia/synthetic-video-detector","name":"synthetic-video-detector","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"synthetic-video-detector","type":"chat"},{"id":"nvidia/cosmos-transfer2_5-2b","name":"cosmos-transfer2.5-2b","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"cosmos-transfer2.5-2b","type":"chat"},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.15},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":-1,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","display_name":"Nemotron 3 Nano Omni","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/llama-3.1-nemotron-nano-8b-v1","name":"Llama 3.1 Nemotron Nano 8B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-03-18","last_updated":"2025-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Llama 3.1 Nemotron Nano 8B v1","type":"chat"},{"id":"nvidia/active-speaker-detection","name":"Active Speaker Detection","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"Active Speaker Detection","type":"chat"},{"id":"nvidia/streampetr","name":"streampetr","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"streampetr","type":"chat"},{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","name":"llama-nemotron-rerank-vl-1b-v2","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"nemotron","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/llama-nemotron-rerank-vl-1b-v2","display_name":"llama-nemotron-rerank-vl-1b-v2","type":"chat"},{"id":"nvidia/nemotron-mini-4b-instruct","name":"nemotron-mini-4b-instruct","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-08-21","last_updated":"2024-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-mini-4b-instruct","display_name":"nemotron-mini-4b-instruct","type":"chat"},{"id":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","description":"Vision language model for physical-world understanding with structured reasoning on video and images","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0},"display_name":"Cosmos Reason2 8B","type":"chat"},{"id":"nvidia/nemotron-3-content-safety","name":"nemotron-3-content-safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-content-safety","display_name":"nemotron-3-content-safety","type":"chat"},{"id":"nvidia/nemotron-3.5-super-vl-120b-a12b","name":"Nemotron 3.5 Super VL 120B A12B","description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","display_name":"Nemotron 3.5 Super VL 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","name":"Llama 3.3 Nemotron Super 49B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-04-07","last_updated":"2025-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/llama-3.3-nemotron-super-49b-v1","display_name":"Llama 3.3 Nemotron Super 49B v1","type":"chat"},{"id":"nvidia/magpie-tts-zeroshot","name":"magpie-tts-zeroshot","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-05-22","last_updated":"2025-06-12","modalities":{"input":["text","audio"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"magpie-tts-zeroshot","type":"chat"},{"id":"nvidia/riva-translate-4b-instruct-v1.1","name":"riva-translate-4b-instruct-v1_1","description":"Translation model for multilingual conversion, localization, and cross-language workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-12-12","last_updated":"2025-12-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"riva-translate-4b-instruct-v1_1","type":"chat"},{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"Nemotron Nano 12B v2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-nano-12b-v2-vl","display_name":"Nemotron Nano 12B v2 VL","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-content-safety","display_name":"Nemotron 3.5 Content Safety","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"status":"deprecated","cost":{"input":0,"output":0},"canonical_model_id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","display_name":"Llama 3.3 Nemotron Super 49B v1.5","type":"chat"},{"id":"nvidia/llama-3_2-nemoretriever-300m-embed-v1","name":"llama-3_2-nemoretriever-300m-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-07-24","last_updated":"2025-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"display_name":"llama-3_2-nemoretriever-300m-embed-v1","type":"chat"},{"id":"nvidia/gliner-pii","name":"gliner-pii","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"gliner-pii","type":"chat"},{"id":"nvidia/usdcode","name":"usdcode","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-01","last_updated":"2026-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"usdcode","type":"chat"},{"id":"nvidia/usdvalidate","name":"usdvalidate","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-07-24","last_updated":"2025-01-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"usdvalidate","type":"chat"},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/llama-3.1-nemotron-70b-instruct","display_name":"Llama 3.1 Nemotron 70B Instruct","type":"chat"},{"id":"nvidia/rerank-qa-mistral-4b","name":"rerank-qa-mistral-4b","description":"Reranking model for improving retrieval quality in search and recommendation systems","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-03-17","last_updated":"2025-01-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"display_name":"rerank-qa-mistral-4b","type":"chat"},{"id":"qwen/qwen-image-edit","name":"Qwen Image Edit","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen Image Edit","type":"image-generation"},{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":66536},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Qwen3 Coder 480B A35B Instruct","type":"chat"},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-01","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Qwen3-Next-80B-A3B-Instruct","type":"chat"},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Qwen3.5-397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32b Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-06","last_updated":"2024-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Qwen2.5 Coder 32b Instruct","type":"chat"},{"id":"qwen/qwen-image","name":"Qwen Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen Image","type":"image-generation"},{"id":"openai/whisper-large-v3","name":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2023-09","release_date":"2023-09-01","last_updated":"2025-09-05","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0,"output":0},"display_name":"Whisper Large v3","type":"chat"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"microsoft/phi-4-mini-instruct","name":"Phi-4-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-01","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Phi-4-Mini","type":"chat"},{"id":"microsoft/phi-4-multimodal-instruct","name":"Phi 4 Multimodal","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Phi 4 Multimodal","type":"chat"}]},"pioneer":{"id":"pioneer","api":"https://api.fastino.ai/v1","name":"Pioneer","doc":"https://agent.pioneer.ai/llms.txt","display_name":"Pioneer","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":1.25,"output":3.75,"cache_read":0.25,"cache_write":1.5625},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0.2},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25,"cache_write":2.5},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"ministral-3b","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2024-10-16","last_updated":"2024-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"canonical_model_id":"mistral/ministral-3b","display_name":"Ministral 3B","type":"chat"},{"id":"magistral-medium","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":2,"output":5,"cache_read":2,"cache_write":2},"canonical_model_id":"mistral/magistral-medium-latest","display_name":"Magistral Medium (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025,"cache_write":0.25},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-3-7-sonnet-latest","name":"Claude Sonnet 3.7","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-3-7-sonnet-20250219","display_name":"Claude Sonnet 3.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":1.75},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0.1},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"mistral-medium-3.5","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":1.5,"output":7.5,"cache_read":1.5,"cache_write":1.5},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0.05},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.5},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude Opus 4.1 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":131072},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":1.25},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.15},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"gemini-3-flash","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.083333},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_read":0.0375,"cache_write":0.234375},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistral-large-3","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.5,"output":1.5,"cache_read":0.5,"cache_write":0.5},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"devstral-small-2","name":"Devstral Small 2","description":"Compact multimodal coding model for repository exploration, file editing, and software agents","family":"devstral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.1,"cache_write":0.1},"canonical_model_id":"mistral/devstral-small-2","display_name":"Devstral Small 2","type":"chat"},{"id":"devstral-2","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.4,"cache_write":0.4},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":1,"cache_write":2},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"mistral-medium","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.4,"output":2,"cache_read":0.4,"cache_write":0.4},"canonical_model_id":"mistral/mistral-medium-2505","display_name":"Mistral Medium 3","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":240000,"output":64000},"cost":{"input":1.04,"output":6.24,"cache_read":0.208,"cache_write":1.3},"canonical_model_id":"alibaba/qwen3.6-max-preview","display_name":"Qwen3.6 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.2,"cache_write":0.4},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-5-fast","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.325,"output":1.95,"cache_read":0.065,"cache_write":0.40625},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"ministral-14b","name":"Ministral 14B","description":"Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"canonical_model_id":"mistral/ministral-14b","display_name":"Ministral 14B","type":"chat"},{"id":"gemini-3.1-pro","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"summary","continuation":["thinking_blocks"],"interleaved":true,"summaries":true}}},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0.25},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01,"cache_write":0.1},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"meta-llama/Llama-3.2-1B-Instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-31","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":60000},"cost":{"input":0.1,"output":0.201,"cache_read":0.1,"cache_write":0.1},"display_name":"Llama 3.2 1B Instruct","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta-llama/Llama-3.2-3B-Instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-31","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":80000},"cost":{"input":0.1,"output":0.335,"cache_read":0.1,"cache_write":0.1},"display_name":"Llama 3.2 3B Instruct","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta-llama/Llama-3.1-8B-Instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2023-12-31","release_date":"2024-06-30","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"display_name":"Llama 3.1 8B Instruct","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta-llama/Llama-3.2-3B","name":"Llama-3.2-3B","description":"Small open Llama base model for lightweight text generation and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"canonical_model_id":"meta/llama-3.2-3b","display_name":"Llama-3.2-3B","type":"chat"},{"id":"meta-llama/Llama-3.2-1B","name":"Llama-3.2-1B","description":"Compact open Llama base model for lightweight and on-device use","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"canonical_model_id":"meta/llama-3.2-1b","display_name":"Llama-3.2-1B","type":"chat"},{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.9,"output":0.9,"cache_read":0.9,"cache_write":0.9},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131000},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0.435},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0.14},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.5,"output":1.2,"cache_read":0.1,"cache_write":0.5},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":1.25},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"HuggingFaceTB/SmolLM3-3B-Base","name":"SmolLM3 3B Base","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"SmolLM3 3B Base","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/diffusiongemma-26B-A4B-it","name":"DiffusionGemma 26B-A4B IT","description":"Gemini model for general assistance, reasoning, and multimodal workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5},"display_name":"DiffusionGemma 26B-A4B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-4-12B-it","name":"Gemma 4 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.25,"output":0.25,"cache_read":0.25,"cache_write":0.25},"display_name":"Gemma 4 12B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-4-E2B-it","name":"Gemma 4 E2B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"canonical_model_id":"google/gemma-4-E2B-it","display_name":"Gemma 4 E2B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-3-4b-pt","name":"Gemma 3 4B (Pretrained)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-02-28","last_updated":"2025-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"Gemma 3 4B (Pretrained)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"google/gemma-4-E4B-it","name":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"canonical_model_id":"google/gemma-4-E4B-it","display_name":"Gemma 4 E4B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-4B-Instruct-2507","name":"Qwen3 4B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"display_name":"Qwen3 4B Instruct","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen2.5-Coder-0.5B","name":"Qwen2.5-Coder-0.5B","description":"Tiny open Qwen code model for lightweight completion and on-device coding","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"canonical_model_id":"alibaba/qwen2.5-coder-0.5b","display_name":"Qwen2.5-Coder-0.5B","type":"chat"},{"id":"Qwen/Qwen3-1.7B-Base","name":"Qwen3 1.7B Base","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"display_name":"Qwen3 1.7B Base","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":1,"cache_read":0.028,"cache_write":0.175},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":1.2,"output":1.2,"cache_read":1.2,"cache_write":1.2},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen3-8B","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-03-31","release_date":"2025-03-31","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"display_name":"Qwen3 8B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-4B-Base","name":"Qwen3 4B Base","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"Qwen3 4B Base","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.9,"output":0.9,"cache_read":0.9,"cache_write":0.9},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":0.3,"cache_read":0.3,"cache_write":0.3},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.6,"output":0.6,"cache_read":0.6,"cache_write":0.6},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"LiquidAI/LFM2-24B-A2B","name":"LFM2 24B A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"liquid","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-01-31","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.03,"output":0.12,"cache_read":0.03,"cache_write":0.03},"display_name":"LFM2 24B A2B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":131072},"cost":{"input":0.56,"output":1.68,"cache_read":0.56,"cache_write":0.56},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek-V3.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.0197,"cache_write":0.1},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0.435},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.27,"output":1.12,"cache_read":0.135,"cache_write":0.27},"canonical_model_id":"deepseek/deepseek-v3","display_name":"DeepSeek-V3","type":"chat"},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.3},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.279,"output":1.2,"cache_read":0.279,"cache_write":0.279},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.15},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistralai/Pixtral-12B-2409","name":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-01","last_updated":"2024-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"canonical_model_id":"mistral/pixtral-12b","display_name":"Pixtral 12B","type":"chat"},{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.02,"output":0.03,"cache_read":0.02,"cache_write":0.02},"canonical_model_id":"mistral/mistral-nemo","display_name":"Mistral Nemo","type":"chat"},{"id":"mistralai/Magistral-Small-2506","name":"Magistral Small","description":"Open Mistral reasoning model for transparent step-by-step problem solving","family":"magistral","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":0.5,"output":1.5,"cache_read":0.5,"cache_write":0.5},"canonical_model_id":"mistral/magistral-small-2506","display_name":"Magistral Small","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistralai/Ministral-8B-Instruct-2410","name":"Ministral 8B Instruct","description":"Efficient open Mistral edge model for on-device chat and function calling","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-10-16","last_updated":"2024-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"canonical_model_id":"mistral/ministral-8b-instruct-2410","display_name":"Ministral 8B Instruct","type":"chat"},{"id":"mistralai/Codestral-22B-v0.1","name":"Codestral-22B-v0.1","description":"Open Mistral code model for fill-in-the-middle and 80+ programming languages","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2024-05-29","last_updated":"2024-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.3,"output":0.9,"cache_read":0.3,"cache_write":0.3},"canonical_model_id":"mistral/codestral-22b-v0.1","display_name":"Codestral-22B-v0.1","type":"chat"},{"id":"mistralai/Mistral-7B-Instruct-v0.3","name":"Mistral 7B Instruct v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2023-04-30","last_updated":"2023-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"display_name":"Mistral 7B Instruct v0.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":131072},"cost":{"input":0.95,"output":4,"cache_read":0.34,"cache_write":0.95},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/Kimi-K3-Fast","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45,"cache_write":4.5},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":0.95},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202000,"output":131072},"cost":{"input":0.98,"output":3.08,"cache_read":0.182,"cache_write":0.98},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1040000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":1.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.2-Fast","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":2.1,"output":6.6,"cache_read":0.21,"cache_write":2.1},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","name":"Nemotron 3.5 Super VL 120B A12B","description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4096},"cost":{"input":0.08,"output":0.45,"cache_read":0.04,"cache_write":0.08},"canonical_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","display_name":"Nemotron 3.5 Super VL 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.05,"output":0.2,"cache_read":0.05,"cache_write":0.05},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65000},"cost":{"input":0.5,"output":2.5,"cache_read":0.15,"cache_write":0.5},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.09,"output":0.45,"cache_read":0.09,"cache_write":0.09},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"pioneer/auto","name":"Pioneer Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2025-06-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":4096},"display_name":"Pioneer Auto","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"fastino/gliner2-multi-v1","name":"GLiNER2 Multi","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-11-30","last_updated":"2025-11-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER2 Multi","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliner2.5-base-v1","name":"GLiNER 2.5 Base","description":"English boundary NER and structured extraction with LoRA fine-tuning.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-24","last_updated":"2026-08-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0.03,"output":0,"cache_read":0.03,"cache_write":0.03},"display_name":"GLiNER 2.5 Base","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliner2-privacy-filter-PII-multi","name":"GLiNER2 Privacy Filter PII (Multi)","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER2 Privacy Filter PII (Multi)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliner2.5-multi-v1","name":"GLiNER 2.5 Multi","description":"Multilingual boundary NER and span extraction; non-trainable encoder.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-24","last_updated":"2026-08-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER 2.5 Multi","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliguard-LLMGuardrails-300M","name":"GLiGuard LLM Guardrails 300M","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiGuard LLM Guardrails 300M","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliner2-large-v1","name":"GLiNER2 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER2 Large","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliner2-base-v1","name":"GLiNER2 Base","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER2 Base","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliguard-PII-multi","name":"GLiNER2-Guardrails-PII-Multi","description":"A 300M-parameter multilingual model that runs LLM safety moderation and PII detection in a single forward pass.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER2-Guardrails-PII-Multi","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/gliner2-multi-large-v1","name":"GLiNER2 Multi Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-11-30","last_updated":"2025-11-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER2 Multi Large","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fastino/GLiNER-2.5-Decide","name":"GLiNER-2.5-Decide","description":"Classification-tuned GLiNER2 large. Entities, relations, and JSON extraction still work.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-24","last_updated":"2026-09-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"display_name":"GLiNER-2.5-Decide","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.07,"output":0.3,"cache_read":0.035,"cache_write":0.07},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.15},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"xiaomi":{"id":"xiaomi","api":"https://api.xiaomimimo.com/v1","name":"Xiaomi","doc":"https://platform.xiaomimimo.com/#/docs","display_name":"Xiaomi","models":[{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"MiMo Pro model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2-flash","name":"MiMo-V2-Flash","description":"Legacy model retained for compatibility with older integrations","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-16","last_updated":"2026-06-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"display_name":"MiMo-V2-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-06-24","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2-omni","name":"MiMo-V2-Omni","description":"Legacy model retained for compatibility with older integrations","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-06-24","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"status":"deprecated","cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"display_name":"MiMo-V2-Omni","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.6-pro-ultraspeed","name":"MiMo-V2.6-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":4.35,"output":8.7,"cache_read":0.036},"display_name":"MiMo-V2.6-Pro-UltraSpeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-06-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"display_name":"MiMo-V2-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-06-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"display_name":"MiMo-V2.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-pro-ultraspeed","name":"MiMo-V2.5-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-06-08","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":1.305,"output":2.61,"cache_read":0.0108},"display_name":"MiMo-V2.5-Pro-UltraSpeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"xiaomi-token-plan-sgp":{"id":"xiaomi-token-plan-sgp","api":"https://token-plan-sgp.xiaomimimo.com/v1","name":"Xiaomi Token Plan (Singapore)","doc":"https://platform.xiaomimimo.com/#/docs","display_name":"Xiaomi Token Plan (Singapore)","models":[{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS-VoiceClone","type":"chat"},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2-tts","name":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2-TTS","type":"chat"},{"id":"mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2-pro","display_name":"MiMo-V2-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-tts","name":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS","type":"chat"},{"id":"mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"display_name":"MiMo-V2.5-TTS-VoiceDesign","type":"chat"},{"id":"mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"minimax":{"id":"minimax","api":"https://api.minimax.io/anthropic/v1","name":"MiniMax (minimax.io)","doc":"https://platform.minimax.io/docs/guides/quickstart","display_name":"MiniMax (minimax.io)","models":[{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"MiniMax-M2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"display_name":"MiniMax-M2","type":"chat"},{"id":"MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375},"display_name":"MiniMax-M2.5-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"github-copilot":{"id":"github-copilot","api":"https://api.githubcopilot.com","name":"GitHub Copilot","doc":"https://docs.github.com/en/copilot","display_name":"GitHub Copilot","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":372000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":32000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":264000,"input":128000,"output":64000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":64000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]},{"type":"budget_tokens","min":256,"max":32000}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"mai-code-1-flash-picker","name":"MAI-Code-1-Flash","description":"Microsoft coding model built for fast, efficient assistance in everyday developer workflows","family":"mai","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-06-02","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":128000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"microsoft/mai-code-1-flash","display_name":"MAI-Code-1-Flash","type":"chat"},{"id":"mai-code-1.1-flash","name":"MAI-Code-1.1-Flash","description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","family":"mai","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":128000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02},"canonical_model_id":"microsoft/mai-code-1.1-flash","display_name":"MAI-Code-1.1-Flash","type":"chat"},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":136000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":372000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]},{"type":"budget_tokens","min":256,"max":24000}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":128000,"output":64000},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":32000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.githubcopilot.com/v1"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":224000,"output":32000},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":372000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"inferx":{"id":"inferx","api":"https://model.inferx.net/endpoints/v1","name":"InferX","doc":"https://model.inferx.net/endpoints","display_name":"InferX","models":[{"id":"gemma-4-31B-it-fp8","name":"Gemma 4 31B IT FP8","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT FP8","type":"chat"},{"id":"Qwen3.6-35B-A3B-fp8-no-thinking","name":"Qwen3.6-35B-A3B-fp8-no-thinking","description":"Qwen3.6-35B-A3B-fp8 disable thinking","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6-35B-A3B-fp8-no-thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Devstral-2-123B-Instruct-2512-int4-AutoRound","name":"Devstral-2-123B-Instruct-2512-int4-AutoRound","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral-2-123B-Instruct-2512-int4-AutoRound","type":"chat"},{"id":"Qwen3.6-27B-FP8","name":"Qwen3.6 27B FP8","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B FP8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen3-Coder-Next-FP8","name":"Qwen3 Coder Next FP8","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256144,"output":65536},"cost":{"input":0,"output":0},"display_name":"Qwen3 Coder Next FP8","type":"chat"},{"id":"Qwen3-Coder-Next-FP8-no-thinking","name":"Qwen3-Coder-Next-FP8-no-thinking","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":260000,"output":65536},"cost":{"input":0,"output":0},"display_name":"Qwen3-Coder-Next-FP8-no-thinking","type":"chat"},{"id":"mimo-v25","name":"mimo-v25","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":100000},"cost":{"input":0,"output":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"mimo-v25","type":"chat"},{"id":"Qwen3-Embedding-8B","name":"Qwen3-Embedding-8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen3-Embedding-8B","type":"embedding"},{"id":"Qwen3.6-35B-A3B-FP8","name":"Qwen3.6 35B A3B FP8","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B FP8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Ornith-1.0-35B-FP8","name":"Ornith-1.0-35B-FP8","description":"Large coding-reasoning model for agentic software tasks and RL search","family":"ornith","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-25","last_updated":"2026-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":100000},"cost":{"input":0,"output":0},"canonical_model_id":"deepreinforce/ornith-1.0-35b","display_name":"Ornith-1.0-35B-FP8","type":"chat"},{"id":"Agents-A1","name":"Agents-A1","description":"35B MoE agentic model built for long-horizon search, engineering, and scientific reasoning tasks","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"release_date":"2026-06-26","last_updated":"2026-06-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":100000},"cost":{"input":0,"output":0},"display_name":"Agents-A1","type":"chat"},{"id":"deepseek-v4-flash","name":"deepseek-v4-flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":100000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"deepseek-v4-flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"opencode-go":{"id":"opencode-go","api":"https://opencode.ai/inference/go/openai/v1","name":"OpenCode Go","doc":"https://opencode.ai/v2/docs/console/go/","display_name":"OpenCode Go","models":[{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5","name":"MiMo V2.5","description":"MiMo omni model for text, image, video, audio, and agents","family":"mimo-v2.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"display_name":"MiMo V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"longcat-2.5-preview-free","name":"LongCat 2.5 Preview Free","description":"Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window","family":"longcat","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-25","last_updated":"2026-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"meituan/longcat-2.5-preview","display_name":"LongCat 2.5 Preview Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-4-argon-contributor","name":"Gemini 4 Argon Contributor","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/go/google/v1beta"},"cost":{"input":4,"output":20,"cache_read":0.2,"input_audio":4},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon Contributor","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows","family":"qwen3.8-max","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/go/anthropic/v1"},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"step-5-preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":1,"output":2.7,"cache_read":0.1},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"longcat-2.0","name":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"meituan/longcat-2.0","display_name":"LongCat-2.0","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"cat-jam-free","name":"Cat Jam Free","description":"A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Cat Jam Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"space-bunny","name":"Space Bunny","description":"Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":524288,"output":524288},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.15,"output":0.6,"cache_read":0.03,"cache_write":0},"display_name":"Space Bunny","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-m2.7","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/go/anthropic/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo-v2.5-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"display_name":"MiMo V2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/go/anthropic/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/go/anthropic/v1"},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2 Contributor","type":"chat"},{"id":"beam-free","name":"Beam Free","description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-06-30","release_date":"2026-10-05","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"reflection/beam-1.0-501b-a23b","display_name":"Beam Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/go/anthropic/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro (New)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"display_name":"DeepSeek V4 Pro (New)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":64000},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.3 Contributor","type":"chat"},{"id":"step-5-preview-free","name":"Step 5 Preview Free","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.7-plus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/go/anthropic/v1"},"cost":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}},"display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"openreason":{"id":"openreason","api":"https://api.openreason.app/v1","name":"OpenReason","doc":"https://openreason.app/docs","display_name":"OpenReason","models":[{"id":"deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.1371,"output":0.2743},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.0022,"output":4.22},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1055,"output":0.422},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"lmstudio":{"id":"lmstudio","api":"http://127.0.0.1:1234/v1","name":"LMStudio","doc":"https://lmstudio.ai/models","display_name":"LMStudio","models":[{"id":"qwen/qwen3-30b-a3b-2507","name":"Qwen3 30B A3B 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"display_name":"Qwen3 30B A3B 2507","type":"chat"},{"id":"qwen/qwen3-coder-30b","name":"Qwen3 Coder 30B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"display_name":"Qwen3 Coder 30B","type":"chat"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"aki-io":{"id":"aki-io","api":"https://aki.io/v1","name":"AKI.IO","doc":"https://aki.io/docs/","display_name":"AKI.IO","models":[{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.3,"output":2.2,"cache_read":0.1},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen3.6-35b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.15,"output":0.5},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm5.3-754b","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":81920},"cost":{"input":1,"output":3.5,"cache_read":0.25},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"mistral4-119b","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.2,"output":0.6},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"deepseek-v4.1-flash-552b","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":81920},"cost":{"input":0.25,"output":1,"cache_read":0.1},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.15,"output":0.55},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemma4-26b","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.1,"output":0.5},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"}]},"tensorx":{"id":"tensorx","api":"https://api.tensorx.ai/v1","name":"TensorX","doc":"https://docs.tensorx.ai/","display_name":"TensorX","models":[{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.25,"output":0.3,"cache_read":0.06},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.5,"output":1.5,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":2,"output":4,"cache_read":0.5},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.75,"output":3.5,"cache_read":0.4375,"cache_write":2.185},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1-0528","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":8192},"cost":{"input":0.66,"output":2.6,"cache_read":0.165,"cache_write":0.825},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek R1-0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.3,"output":0.5,"cache_read":0.075,"cache_write":0.375},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.3,"cache_write":1.5},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM-5V-Turbo","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1,"output":3.2,"cache_read":0.25,"cache_write":1.25},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.5,"output":4.5,"cache_read":0.375},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.4,"output":4.4,"cache_read":0.35,"cache_write":1.75},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.3,"cache_write":1.5},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":1.75,"output":4.5,"cache_read":0.44},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.75},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1,"output":4,"cache_read":0.25,"cache_write":1.25},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.8,"cache_read":0.125,"cache_write":0.625},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.25,"output":4.5,"cache_read":0.3125},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":65536},"cost":{"input":0.3,"output":1.2,"cache_read":0.075,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.1},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen3 235B-A22B-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":262144},"cost":{"input":0.072,"output":0.464,"cache_read":0.018,"cache_write":0.09},"display_name":"Qwen3 235B-A22B-2507","type":"chat"},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.4,"output":2.4,"cache_read":0.1},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":2.5,"output":6,"cache_read":0.63},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":3.5,"cache_read":0.125,"cache_write":0.625},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.15,"output":0.2,"cache_read":0.0375,"cache_write":0.1875},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-flash-next","name":"Qwen3.8 Flash Next","description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.8-flash-next","display_name":"Qwen3.8 Flash Next","type":"chat"}]},"longcat":{"id":"longcat","api":"https://api.longcat.chat/openai","name":"LongCat","doc":"https://longcat.chat/platform/docs/","display_name":"LongCat","models":[{"id":"LongCat-2.0","name":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.75,"output":2.95,"cache_read":0.015},"canonical_model_id":"meituan/longcat-2.0","display_name":"LongCat-2.0","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"pareto":{"id":"pareto","api":"https://api.paretoinference.com/v1","name":"Pareto Inference","doc":"https://docs.paretoinference.com/","display_name":"Pareto Inference","models":[{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.03,"output":0.1,"cache_read":0.006},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"chutes":{"id":"chutes","api":"https://llm.chutes.ai/v1","name":"Chutes","doc":"https://llm.chutes.ai/v1/models","display_name":"Chutes","models":[{"id":"Nemotron-3-Nano-Omni-30B-TEE","name":"Nemotron 3 Nano Omni 30B TEE","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.0245,"output":0.0978,"cache_read":0.0024499999999999995},"display_name":"Nemotron 3 Nano Omni 30B TEE","type":"chat"},{"id":"unsloth/Mistral-Nemo-Instruct-2407-TEE","name":"Mistral Nemo Instruct 2407 TEE","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0245,"output":0.0978,"cache_read":0.0024499999999999995},"canonical_model_id":"mistral/mistral-nemo","display_name":"Mistral Nemo Instruct 2407 TEE","type":"chat"},{"id":"google/gemma-4-31B-turbo-TEE","name":"gemma 4 31B turbo TEE","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.12,"output":0.37,"cache_read":0.011999999999999997},"canonical_model_id":"google/gemma-4-31b-it","display_name":"gemma 4 31B turbo TEE","type":"chat"},{"id":"Qwen/Qwen3-32B-TEE","name":"Qwen3 32B TEE","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0.104,"output":0.416,"cache_read":0.010399999999999998},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B TEE","type":"chat"},{"id":"Qwen/Qwen3.6-27B-TEE","name":"Qwen3.6 27B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2,"cache_read":0.024999999999999994},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","name":"Qwen3 235B A22B Thinking 2507 TEE","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07","last_updated":"2026-06-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2989,"output":1.1957,"cache_read":0.029889999999999993},"display_name":"Qwen3 235B A22B Thinking 2507 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.8-27B-TEE","name":"Qwen3.8 27B TEE","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-16","last_updated":"2026-08-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.039,"output":1.25,"cache_read":0.003899999999999999},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B TEE","type":"chat"},{"id":"Qwen/Qwen3.5-397B-A17B-TEE","name":"Qwen3.5 397B A17B TEE","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":3,"cache_read":0.04499999999999999},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B A17B TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","name":"DeepSeek V4 Flash 0731 TEE","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.44,"output":1.32,"cache_read":0.04399999999999999},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 TEE","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.2-TEE","name":"DeepSeek V3.2 TEE","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12","last_updated":"2026-06-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":1,"output":1,"cache_read":0.09999999999999998},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K3-TEE","name":"Kimi K3 TEE","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65535},"cost":{"input":1.85,"output":9.5,"cache_read":0.18499999999999997},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 TEE","type":"chat"},{"id":"moonshotai/Kimi-K2.6-TEE","name":"Kimi K2.6 TEE","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65535},"cost":{"input":0.45,"output":1.95,"cache_read":0.04499999999999999},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.2-TEE","name":"GLM 5.2 TEE","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65535},"cost":{"input":1.25,"output":3.95,"cache_read":0.12499999999999997},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.1-TEE","name":"GLM 5.1 TEE","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":65535},"cost":{"input":0.98,"output":3.08,"cache_read":0.09799999999999998},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM 5.1 TEE","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"edenai":{"id":"edenai","api":"https://api.edenai.run/v3","name":"Eden AI","doc":"https://docs.edenai.co","display_name":"Eden AI","models":[{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepinfra/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B (Deep Infra)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.085,"output":0.4},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B (Deep Infra)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.5,"output":2.2,"cache_read":0.1},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/meta-models/Muse-Glimmer-30B","name":"Muse Glimmer 30B (Deep Infra)","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B (Deep Infra)","type":"chat"},{"id":"deepinfra/tencent/Hy3","name":"Hy3 (Deep Infra)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.13,"output":0.53,"cache_read":0.033},"canonical_model_id":"tencent/hy3","display_name":"Hy3 (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/tencent/Hy4-preview","name":"Hy4 preview (Deep Infra)","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/meta-llama/Llama-Guard-3-8B","name":"Llama-Guard-3-8B (Deep Infra)","description":"Llama 3.1-based safety classifier for moderating prompts and model responses","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.055,"output":0.055},"canonical_model_id":"meta/llama-guard-3-8b","display_name":"Llama-Guard-3-8B (Deep Infra)","type":"chat"},{"id":"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","name":"Llama-3.2-11B-Vision-Instruct (Deep Infra)","description":"Open multimodal Llama model for image understanding, captioning, and visual QA","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.345,"output":0.345},"canonical_model_id":"meta/llama-3.2-11b-vision-instruct","display_name":"Llama-3.2-11B-Vision-Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct (Deep Infra)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.1,"output":0.32},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/thinkingmachines/Inkling-Small","name":"Inkling Small (Deep Infra)","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small (Deep Infra)","type":"chat"},{"id":"deepinfra/thinkingmachines/Inkling","name":"Inkling (Deep Infra)","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling (Deep Infra)","type":"chat"},{"id":"deepinfra/google/gemma-3-27b-it","name":"Gemma 3 27B IT (Deep Infra)","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.08,"output":0.16},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT (Deep Infra)","type":"chat"},{"id":"deepinfra/google/gemma-3-12b-it","name":"Gemma 3 12B IT (Deep Infra)","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.15},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT (Deep Infra)","type":"chat"},{"id":"deepinfra/google/gemma-3-4b-it","name":"Gemma 3 4B IT (Deep Infra)","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.1},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B IT (Deep Infra)","type":"chat"},{"id":"deepinfra/Gryphe/MythoMax-L2-13b","name":"MythoMax L2 13B (Deep Infra)","description":"Llama 2 merge combining MythoLogic and Huginn for creative writing and roleplay","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2023-08-10","last_updated":"2023-08-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":3200},"cost":{"input":0.4,"output":0.4},"canonical_model_id":"gryphe/mythomax-l2-13b","display_name":"MythoMax L2 13B (Deep Infra)","type":"chat"},{"id":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct (Deep Infra)","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3-Next 80B-A3B Instruct (Deep Infra)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.09,"output":1.1},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen3 VL 30B A3B Instruct (Deep Infra)","description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"alibaba/qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/Qwen/Qwen3-Max","name":"Qwen3 Max (Deep Infra)","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.2,"output":6,"cache_read":0.24},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507 (Deep Infra)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.09,"output":0.55},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507 (Deep Infra)","type":"chat"},{"id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3-Coder 480B-A35B Instruct (Deep Infra)","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":1.6},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3-Coder 480B-A35B Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731 (Deep Infra)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.06,"output":0.18,"cache_read":0.015},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/deepseek-ai/DeepSeek-R1","name":"DeepSeek-R1 (Deep Infra)","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.7,"output":2.4},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1 (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813 (Deep Infra)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash (Deep Infra)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.2,"output":0.6,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 0528 (Deep Infra)","description":"May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.5,"output":2.15,"cache_read":0.35},"canonical_model_id":"deepseek/deepseek-r1-0528","display_name":"DeepSeek R1 0528 (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash 1017 (Deep Infra)","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.2,"output":0.6,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017 (Deep Infra)","type":"chat"},{"id":"deepinfra/deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3 (Deep Infra)","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.32,"output":0.89},"canonical_model_id":"deepseek/deepseek-v3","display_name":"DeepSeek-V3 (Deep Infra)","type":"chat"},{"id":"deepinfra/deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324 (Deep Infra)","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.24,"output":0.9,"cache_read":0.135},"canonical_model_id":"deepseek/deepseek-v3-0324","display_name":"DeepSeek V3 0324 (Deep Infra)","type":"chat"},{"id":"deepinfra/stepfun-ai/Step-3.7-Flash","name":"Step 3.7 Flash (Deep Infra)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash (Deep Infra)","type":"chat"},{"id":"deepinfra/stepfun-ai/Step-5-Preview","name":"Step 5 Preview (Deep Infra)","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1000000},"cost":{"input":1,"output":2.7,"cache_read":0.1},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview (Deep Infra)","type":"chat"},{"id":"deepinfra/stepfun-ai/Step-3.5-Flash","name":"Step 3.5 Flash (Deep Infra)","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.09,"output":0.3,"cache_read":0.02},"canonical_model_id":"stepfun/step-3.5-flash","display_name":"Step 3.5 Flash (Deep Infra)","type":"chat"},{"id":"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","name":"Mistral Small 3 (Deep Infra)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.05,"output":0.08},"canonical_model_id":"mistral/mistral-small-24b-instruct-2501","display_name":"Mistral Small 3 (Deep Infra)","type":"chat"},{"id":"deepinfra/moonshotai/Kimi-K2-Instruct","name":"Kimi K2 Instruct (Deep Infra)","description":"Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":2},"canonical_model_id":"moonshotai/kimi-k2-instruct","display_name":"Kimi K2 Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/moonshotai/Kimi-K2.5","name":"Kimi K2.5 (Deep Infra)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepinfra/zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash (Deep Infra)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","name":"Nemotron 3 Nano 30B A3B (Deep Infra)","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.025},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","name":"Llama 3.1 Nemotron 70B Instruct (Deep Infra)","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.6,"output":0.6},"canonical_model_id":"nvidia/llama-3.1-nemotron-70b-instruct","display_name":"Llama 3.1 Nemotron 70B Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/ByteDance/Seed-2.0-code","name":"Seed 2.0 Code (Deep Infra)","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code (Deep Infra)","type":"chat"},{"id":"deepinfra/ByteDance/Seed-2.0-mini","name":"Seed 2.0 Mini (Deep Infra)","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.1,"output":0.4,"cache_read":0.02},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed 2.0 Mini (Deep Infra)","type":"chat"},{"id":"deepinfra/openai/gpt-oss-20b","name":"GPT OSS 20B (Deep Infra)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.03,"output":0.14},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/openai/gpt-oss-120b","name":"GPT OSS 120B (Deep Infra)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.037,"output":0.17},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Deep Infra)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepinfra/microsoft/WizardLM-2-8x22B","name":"WizardLM 2 8x22B (Deep Infra)","description":"Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-04-15","last_updated":"2024-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":8000},"cost":{"input":0.48,"output":0.48},"canonical_model_id":"microsoft/wizardlm-2-8x22b","display_name":"WizardLM 2 8x22B (Deep Infra)","type":"chat"},{"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","name":"Hermes 3 70B Instruct (Deep Infra)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-18","last_updated":"2024-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.7,"output":0.7},"canonical_model_id":"nousresearch/hermes-3-llama-3.1-70b","display_name":"Hermes 3 70B Instruct (Deep Infra)","type":"chat"},{"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","name":"Hermes 3 405B Instruct (Deep Infra)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-16","last_updated":"2024-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":1,"output":1},"canonical_model_id":"nousresearch/hermes-3-llama-3.1-405b","display_name":"Hermes 3 405B Instruct (Deep Infra)","type":"chat"},{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B (Cerebras)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.35,"output":0.75,"cache_read":0.35},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Cerebras)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/openai/gpt-oss-20b","name":"GPT OSS 20B (Groq)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Groq)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B (Groq)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B (Groq)","type":"chat"},{"id":"groq/openai/gpt-oss-120b","name":"GPT OSS 120B (Groq)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Groq)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM-4.6V","type":"chat"},{"id":"zai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM-5V-Turbo","type":"chat"},{"id":"zai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-latest","name":"Claude Opus Latest (Claude Opus 5.5)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus Latest (Claude Opus 5.5)","type":"chat"},{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-haiku-latest","name":"Claude Haiku Latest (Claude Haiku 5.5)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku Latest (Claude Haiku 5.5)","type":"chat"},{"id":"anthropic/claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-latest","name":"Claude Sonnet Latest (Claude Sonnet 5.5)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet Latest (Claude Sonnet 5.5)","type":"chat"},{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-fable-latest","name":"Claude Fable Latest (Claude Fable 5.1)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable Latest (Claude Fable 5.1)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"cohere/command-r-08-2024","name":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"cohere/command-r-08-2024","display_name":"Command R","type":"chat"},{"id":"cohere/command-a-03-2025","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":288000,"output":8000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-a-03-2025","display_name":"Command A","type":"chat"},{"id":"cohere/command-r7b-12-2024","name":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":132000,"output":4000},"cost":{"input":0.0375,"output":0.15},"canonical_model_id":"cohere/command-r7b-12-2024","display_name":"Command R7B","type":"chat"},{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"canonical_model_id":"cohere/command-r-plus-08-2024","display_name":"Command R+","type":"chat"},{"id":"cohere/c4ai-aya-expanse-32b","name":"Aya Expanse 32B","description":"Open multilingual model optimized for generation across 23 languages","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-10-24","last_updated":"2024-10-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"cohere/c4ai-aya-expanse-32b","display_name":"Aya Expanse 32B","type":"chat"},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-chat","display_name":"DeepSeek Chat","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"databricks/databricks-inkling","name":"Inkling (Databricks)","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1048576},"cost":{"input":1,"output":4.05,"cache_read":0.1,"cache_write":1.00002},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling (Databricks)","type":"chat"},{"id":"databricks/databricks-qwen3-next-80b-a3b-instruct@eu","name":"Qwen3-Next 80B-A3B Instruct (Databricks, EU)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15001,"output":1.20001,"cache_read":0.015001,"cache_write":0.15001},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct (Databricks, EU)","type":"chat"},{"id":"databricks/databricks-gpt-oss-20b","name":"GPT OSS 20B (Databricks)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.30002,"cache_read":0.007,"cache_write":0.07},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Databricks)","type":"chat"},{"id":"databricks/databricks-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 (Databricks)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.014,"cache_write":0.14},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Databricks)","type":"chat"},{"id":"databricks/databricks-gpt-oss-120b@eu","name":"GPT OSS 120B (Databricks, EU)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15001,"output":0.59997,"cache_read":0.015001,"cache_write":0.15001},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Databricks, EU)","type":"chat"},{"id":"databricks/databricks-gpt-oss-120b","name":"GPT OSS 120B (Databricks)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15001,"output":0.59997,"cache_read":0.015001,"cache_write":0.15001},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Databricks)","type":"chat"},{"id":"databricks/databricks-deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813 (Databricks)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.959999,"cache_read":0.132,"cache_write":1.31999},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (Databricks)","type":"chat"},{"id":"databricks/databricks-qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct (Databricks)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15001,"output":1.20001,"cache_read":0.015001,"cache_write":0.15001},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct (Databricks)","type":"chat"},{"id":"databricks/databricks-gpt-oss-20b@eu","name":"GPT OSS 20B (Databricks, EU)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.30002,"cache_read":0.007,"cache_write":0.07},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Databricks, EU)","type":"chat"},{"id":"tencent/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Tencent)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Tencent)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813 (Tencent)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (Tencent)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy3","name":"Hy3 (Tencent)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0.132,"output":0.528,"cache_read":0.033},"canonical_model_id":"tencent/hy3","display_name":"Hy3 (Tencent)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy4-preview","name":"Hy4 preview (Tencent)","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview (Tencent)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together_ai/meta-models/Muse-Glimmer-30B","name":"Muse Glimmer 30B (Together AI)","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B (Together AI)","type":"chat"},{"id":"together_ai/thinkingmachines/Inkling","name":"Inkling (Together AI)","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling (Together AI)","type":"chat"},{"id":"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731 (Together AI)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813 (Together AI)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash (Together AI)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"together_ai/openai/gpt-oss-120b","name":"GPT OSS 120B (Together AI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Together AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"azure/gpt-5.2-codex","name":"GPT-5.2 Codex (Azure)","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.1-codex","name":"GPT-5.1 Codex (Azure)","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1 Codex (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max (Azure)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex-max","display_name":"GPT-5.1 Codex Max (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"azure/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini (Azure)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini (Azure)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"flexai/DeepSeek-V4-Flash-0731@eu","name":"DeepSeek V4 Flash 0731 (FlexAI, EU)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.119,"output":0.238,"cache_read":0.0178},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (FlexAI, EU)","type":"chat"},{"id":"flexai/Step-3.7-Flash","name":"Step 3.7 Flash (FlexAI)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.03},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash (FlexAI)","type":"chat"},{"id":"flexai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731 (FlexAI)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.119,"output":0.238,"cache_read":0.0178},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (FlexAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"flexai/Muse-Glimmer-30B","name":"Muse Glimmer 30B (FlexAI)","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.045},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B (FlexAI)","type":"chat"},{"id":"flexai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash (FlexAI)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.1,"output":0.66,"cache_read":0.015},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (FlexAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"flexai/gpt-oss-20b","name":"GPT OSS 20B (FlexAI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.02,"output":0.1,"cache_read":0.003},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (FlexAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"flexai/gpt-oss-120b","name":"GPT OSS 120B (FlexAI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.25,"cache_read":0.0075},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (FlexAI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest (Gemini 3.8 Flash)","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini Flash Latest (Gemini 3.8 Flash)","type":"chat"},{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image-preview","display_name":"Nano Banana 2 Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["audio","image","text","video"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Nano Banana","type":"image-generation"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro Preview","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2},"canonical_model_id":"google/gemini-3-pro-image-preview","display_name":"Nano Banana Pro Preview","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":1.5},"canonical_model_id":"google/gemini-3.1-flash-lite-image","display_name":"Nano Banana 2 Lite","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/deep-research-preview-04-2026","name":"Gemini Deep Research Preview","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12},"canonical_model_id":"google/deep-research-preview-04-2026","display_name":"Gemini Deep Research Preview","type":"chat"},{"id":"google/deep-research-max-preview-04-2026","name":"Deep Research Max Preview","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12},"canonical_model_id":"google/deep-research-max-preview-04-2026","display_name":"Deep Research Max Preview","type":"chat"},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"reasoning":3,"cache_read":0.05,"cache_write":0.083333,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-pro-latest","name":"Gemini Pro Latest (Gemini 4 Argon)","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":20,"reasoning":20,"cache_read":0.2,"cache_write":0.375,"input_audio":4},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini Pro Latest (Gemini 4 Argon)","type":"chat"},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite-preview","display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"google/gemini-nano-banana-2.1","name":"Nano Banana 2.1","description":"Image model for prompt-driven generation, multi-turn editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"google/gemini-nano-banana-2.1","display_name":"Nano Banana 2.1","type":"image-generation"},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":20,"reasoning":20,"cache_read":0.2,"cache_write":0.375,"input_audio":4},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-latest","name":"Grok Latest (Grok 4.7)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok Latest (Grok 4.7)","type":"chat"},{"id":"xai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"xai/grok-4-fast-non-reasoning","name":"X-Ai/Grok-4-Fast-Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05,"tiers":[{"input":0.4,"output":1,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"xai/grok-4-fast-non-reasoning","display_name":"X-Ai/Grok-4-Fast-Non-Reasoning","type":"chat"},{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nebius/meta-models/muse-spark-open","name":"Muse Spark Open (Nebius)","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":1.25},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open (Nebius)","type":"chat"},{"id":"nebius/google/gemma-3-27b-it","name":"Gemma 3 27B IT (Nebius)","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":110000,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.1},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT (Nebius)","type":"chat"},{"id":"nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507 (Nebius)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.2,"output":0.6,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507 (Nebius)","type":"chat"},{"id":"nebius/deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731 (Nebius)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.14},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Nebius)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nebius/deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813 (Nebius)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":979000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":1.32},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (Nebius)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nebius/deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash (Nebius)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.3},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Nebius)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nebius/nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B (Nebius)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.9,"cache_read":0.3},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B (Nebius)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nebius/nvidia/Nemotron-3-Ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B (Nebius)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":1,"output":3,"cache_read":1},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B (Nebius)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nebius/openai/gpt-oss-120b","name":"GPT OSS 120B (Nebius)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.15},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Nebius)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scaleway/gemma-3-27b-it","name":"Gemma 3 27B IT (Scaleway)","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":40000,"output":131072},"cost":{"input":0.287125,"output":0.57425},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT (Scaleway)","type":"chat"},{"id":"scaleway/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 (Scaleway)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":384000},"cost":{"input":0.45012,"output":0.90024,"cache_read":0.090024},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Scaleway)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scaleway/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B-A22B Instruct 2507 (Scaleway)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":250000,"output":16384},"cost":{"input":0.843975,"output":2.531925},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507 (Scaleway)","type":"chat"},{"id":"scaleway/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Scaleway)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":384000},"cost":{"input":0.67518,"output":2.02554,"cache_read":0.135036},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Scaleway)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"scaleway/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct (Scaleway)","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":65536},"cost":{"input":0.22506,"output":0.90024},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct (Scaleway)","type":"chat"},{"id":"scaleway/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct (Scaleway)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":1.01277,"output":1.01277},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct (Scaleway)","type":"chat"},{"id":"scaleway/gpt-oss-120b","name":"GPT OSS 120B (Scaleway)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.168795,"output":0.67518},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Scaleway)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ionos/meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct (IONOS)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.731445,"output":0.731445},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct (IONOS)","type":"chat"},{"id":"ionos/Qwen/Qwen3-Coder-Next","name":"Qwen3 Coder Next (IONOS)","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":65536},"cost":{"input":0.168795,"output":0.90024},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next (IONOS)","type":"chat"},{"id":"ionos/openai/gpt-oss-120b","name":"GPT OSS 120B (IONOS)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.168795,"output":0.731445},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (IONOS)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"vertex/gemini-4-argon@us","name":"Gemini 4 Argon (Vertex AI, US)","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":20,"reasoning":20,"cache_read":0.2,"cache_write":0.375,"input_audio":4},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon (Vertex AI, US)","type":"chat"},{"id":"vertex/gemini-flash-latest","name":"Gemini Flash Latest (Gemini 3.8 Flash, Vertex AI)","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini Flash Latest (Gemini 3.8 Flash, Vertex AI)","type":"chat"},{"id":"vertex/gemini-2.5-flash-image","name":"Nano Banana (Vertex AI)","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Nano Banana (Vertex AI)","type":"image-generation"},{"id":"vertex/gemini-3.1-flash-lite@eu","name":"Gemini 3.1 Flash Lite (Vertex AI, EU)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite (Vertex AI, EU)","type":"chat"},{"id":"vertex/gemini-3.5-flash-lite@eu","name":"Gemini 3.5 Flash Lite (Vertex AI, EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite (Vertex AI, EU)","type":"chat"},{"id":"vertex/gemini-3.6-flash@eu","name":"Gemini 3.6 Flash (Vertex AI, EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash (Vertex AI, EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.6-flash","name":"Gemini 3.6 Flash (Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-4-argon@eu","name":"Gemini 4 Argon (Vertex AI, EU)","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":20,"reasoning":20,"cache_read":0.2,"cache_write":0.375,"input_audio":4},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon (Vertex AI, EU)","type":"chat"},{"id":"vertex/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite (Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"vertex/gemini-3.1-flash-image","name":"Nano Banana 2 (Vertex AI)","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2 (Vertex AI)","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"vertex/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview (Vertex AI)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":0.25}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.5-flash","name":"Gemini 3.5 Flash (Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3-pro-image","name":"Nano Banana Pro (Vertex AI)","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro (Vertex AI)","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.7-flash@us","name":"Gemini 3.7 Flash (Vertex AI, US)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash (Vertex AI, US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.7-flash@eu","name":"Gemini 3.7 Flash (Vertex AI, EU)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash (Vertex AI, EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite (Vertex AI)","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":1.5},"canonical_model_id":"google/gemini-3.1-flash-lite-image","display_name":"Nano Banana 2 Lite (Vertex AI)","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"vertex/gemini-3.8-flash@eu","name":"Gemini 3.8 Flash (Vertex AI, EU)","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash (Vertex AI, EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.7-flash","name":"Gemini 3.7 Flash (Vertex AI)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.6-flash@us","name":"Gemini 3.6 Flash (Vertex AI, US)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash (Vertex AI, US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.5-flash-lite@us","name":"Gemini 3.5 Flash Lite (Vertex AI, US)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite (Vertex AI, US)","type":"chat"},{"id":"vertex/gemini-3-flash-preview","name":"Gemini 3 Flash Preview (Vertex AI)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"reasoning":3,"cache_read":0.05,"cache_write":0.083333,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.1-flash-lite@us","name":"Gemini 3.1 Flash Lite (Vertex AI, US)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite (Vertex AI, US)","type":"chat"},{"id":"vertex/gemini-pro-latest","name":"Gemini Pro Latest (Gemini 4 Argon, Vertex AI)","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":20,"reasoning":20,"cache_read":0.2,"cache_write":0.375,"input_audio":4},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini Pro Latest (Gemini 4 Argon, Vertex AI)","type":"chat"},{"id":"vertex/gemini-3.8-flash","name":"Gemini 3.8 Flash (Vertex AI)","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.5-flash@eu","name":"Gemini 3.5 Flash (Vertex AI, EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash (Vertex AI, EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.8-flash@us","name":"Gemini 3.8 Flash (Vertex AI, US)","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash (Vertex AI, US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-3.5-flash@us","name":"Gemini 3.5 Flash (Vertex AI, US)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash (Vertex AI, US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"vertex/gemini-nano-banana-2.1","name":"Nano Banana 2.1 (Vertex AI)","description":"Image model for prompt-driven generation, multi-turn editing, and visual design workflows","family":"gemini-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"google/gemini-nano-banana-2.1","display_name":"Nano Banana 2.1 (Vertex AI)","type":"image-generation"},{"id":"vertex/gemini-4-argon","name":"Gemini 4 Argon (Vertex AI)","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":20,"reasoning":20,"cache_read":0.2,"cache_write":0.375,"input_audio":4},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon (Vertex AI)","type":"chat"},{"id":"vertex/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite (Vertex AI)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite (Vertex AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"greenpt/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 (Greenpt)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.157542,"output":0.393855,"cache_read":0.045012},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Greenpt)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"greenpt/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B-A22B Instruct 2507 (Greenpt)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":250000,"output":16384},"cost":{"input":1.01277,"output":3.03831},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507 (Greenpt)","type":"chat"},{"id":"greenpt/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Greenpt)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.247566,"output":1.23783,"cache_read":0.012378},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Greenpt)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"greenpt/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct (Greenpt)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":1.23783,"output":1.23783},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct (Greenpt)","type":"chat"},{"id":"greenpt/gpt-oss-120b","name":"GPT OSS 120B (Greenpt)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.22506,"output":0.78771},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Greenpt)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"greenference/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Greenference)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.22,"output":0.88,"cache_read":0.007},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Greenference)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"greenference/gpt-oss-20b","name":"GPT OSS 20B (Greenference)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.009,"output":0.045,"cache_read":0.0045},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Greenference)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"perplexityai/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"canonical_model_id":"perplexity/sonar-pro","display_name":"Sonar Pro","type":"chat"},{"id":"perplexityai/sonar-deep-research","name":"Sonar Deep Research","description":"Sonar search model for autonomous research and citation-backed long-form reports","family":"sonar","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"canonical_model_id":"perplexity/sonar-deep-research","display_name":"Sonar Deep Research","type":"chat"},{"id":"perplexityai/sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127072,"output":4096},"cost":{"input":1,"output":1},"canonical_model_id":"perplexity/sonar","display_name":"Sonar","type":"chat"},{"id":"perplexityai/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"canonical_model_id":"perplexity/sonar-reasoning-pro","display_name":"Sonar Reasoning Pro","type":"chat"},{"id":"cloudflare/@cf/meta/llama-guard-3-8b","name":"Llama-Guard-3-8B (Cloudflare)","description":"Llama 3.1-based safety classifier for moderating prompts and model responses","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.484,"output":0.03},"canonical_model_id":"meta/llama-guard-3-8b","display_name":"Llama-Guard-3-8B (Cloudflare)","type":"chat"},{"id":"cloudflare/@cf/meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct (Cloudflare)","description":"Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":60000,"output":32000},"cost":{"input":0.027,"output":0.201},"canonical_model_id":"meta/llama-3.2-1b-instruct","display_name":"Llama 3.2 1B Instruct (Cloudflare)","type":"chat"},{"id":"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","name":"Gemma-SEA-LION-v4-27B-IT (Cloudflare)","description":"Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"canonical_model_id":"aisingapore/gemma-sea-lion-v4-27b-it","display_name":"Gemma-SEA-LION-v4-27B-IT (Cloudflare)","type":"chat"},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 (Cloudflare)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Cloudflare)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813 (Cloudflare)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (Cloudflare)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B (Cloudflare)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":102400},"cost":{"input":0.351,"output":0.555},"canonical_model_id":"mistral/mistral-small-3.1-24b-instruct","display_name":"Mistral Small 3.1 24B (Cloudflare)","type":"chat"},{"id":"cloudflare/@cf/zai-org/glm-4.7-flash","name":"GLM-4.7-Flash (Cloudflare)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0605,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash (Cloudflare)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5-Coder-32B-Instruct (Cloudflare)","description":"Open coding-focused Qwen model for code generation, repair, and repository reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.66,"output":1},"canonical_model_id":"alibaba/qwen2.5-coder-32b-instruct","display_name":"Qwen2.5-Coder-32B-Instruct (Cloudflare)","type":"chat"},{"id":"cloudflare/@cf/openai/gpt-oss-20b","name":"GPT OSS 20B (Cloudflare)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.2,"output":0.3},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (Cloudflare)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cloudflare/@cf/openai/gpt-oss-120b","name":"GPT OSS 120B (Cloudflare)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.35,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Cloudflare)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/MiniMax-M2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/MiniMax-M2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax-M2","type":"chat"},{"id":"tensorx/deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 (TensorX)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.25,"output":0.3,"cache_read":0.0625},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (TensorX)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tensorx/deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (TensorX)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.5,"output":1.5,"cache_read":0.125},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (TensorX)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tensorx/deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813 (TensorX)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":2,"output":4,"cache_read":0.5},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (TensorX)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tensorx/deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528 (TensorX)","description":"May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":32768},"cost":{"input":0.66,"output":2.6,"cache_read":0.165},"canonical_model_id":"deepseek/deepseek-r1-0528","display_name":"DeepSeek R1 0528 (TensorX)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"tensorx/deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017 (TensorX)","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.5,"output":1.5,"cache_read":0.125},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017 (TensorX)","type":"chat"},{"id":"tensorx/moonshotai/kimi-k2.5","name":"Kimi K2.5 (TensorX)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.8,"cache_read":0.125},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 (TensorX)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"amazon/google.gemma-3-12b-it","name":"Gemma 3 12B IT (Amazon Bedrock)","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.09,"output":0.29},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT (Amazon Bedrock)","type":"chat"},{"id":"amazon/google.gemma-3-4b-it","name":"Gemma 3 4B IT (Amazon Bedrock)","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.04,"output":0.08},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B IT (Amazon Bedrock)","type":"chat"},{"id":"amazon/openai.gpt-oss-safeguard-20b@us","name":"GPT OSS Safeguard 20B (Amazon Bedrock, US)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.07,"output":0.2},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/openai.gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B (Amazon Bedrock)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.07,"output":0.2},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B (Amazon Bedrock)","type":"chat"},{"id":"amazon/amazon.nova-lite-v1:0@us","name":"Nova Lite (US)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.06,"output":0.24,"cache_read":0.015},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite (US)","type":"chat"},{"id":"amazon/mistral.voxtral-mini-3b-2507@us","name":"Voxtral Mini 3B 2507 (Amazon Bedrock, US)","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.04,"output":0.04},"canonical_model_id":"mistral/voxtral-mini-3b-2507","display_name":"Voxtral Mini 3B 2507 (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/amazon.nova-micro-v1:0","name":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.035,"output":0.14,"cache_read":0.00875},"canonical_model_id":"amazon/nova-micro","display_name":"Nova Micro","type":"chat"},{"id":"amazon/amazon.nova-pro-v1:0","name":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.8,"output":3.2,"cache_read":0.2},"canonical_model_id":"amazon/nova-pro","display_name":"Nova Pro","type":"chat"},{"id":"amazon/mistral.voxtral-small-24b-2507","name":"Voxtral Small 24B 2507 (Amazon Bedrock)","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/voxtral-small-24b-2507","display_name":"Voxtral Small 24B 2507 (Amazon Bedrock)","type":"chat"},{"id":"amazon/amazon.nova-lite-v1:0","name":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.06,"output":0.24,"cache_read":0.015},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite","type":"chat"},{"id":"amazon/mistral.voxtral-small-24b-2507@us","name":"Voxtral Small 24B 2507 (Amazon Bedrock, US)","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/voxtral-small-24b-2507","display_name":"Voxtral Small 24B 2507 (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/google.gemma-3-12b-it@us","name":"Gemma 3 12B IT (Amazon Bedrock, US)","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.09,"output":0.29},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/google.gemma-3-27b-it","name":"Gemma 3 27B IT (Amazon Bedrock)","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.23,"output":0.38},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT (Amazon Bedrock)","type":"chat"},{"id":"amazon/google.gemma-3-27b-it@us","name":"Gemma 3 27B IT (Amazon Bedrock, US)","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.23,"output":0.38},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/mistral.pixtral-large-2502-v1:0","name":"Pixtral Large (25.02) (Amazon Bedrock)","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-08","last_updated":"2025-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2,"output":6},"canonical_model_id":"mistral/pixtral-large-2502","display_name":"Pixtral Large (25.02) (Amazon Bedrock)","type":"chat"},{"id":"amazon/amazon.nova-micro-v1:0@us","name":"Nova Micro (US)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.035,"output":0.14,"cache_read":0.00875},"canonical_model_id":"amazon/nova-micro","display_name":"Nova Micro (US)","type":"chat"},{"id":"amazon/zai.glm-4.7-flash@us","name":"GLM-4.7-Flash (Amazon Bedrock, US)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131072},"cost":{"input":0.07,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/qwen.qwen3-coder-next","name":"Qwen3 Coder Next (Amazon Bedrock)","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.5,"output":1.2},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next (Amazon Bedrock)","type":"chat"},{"id":"amazon/moonshotai.kimi-k2.5","name":"Kimi K2.5 (Amazon Bedrock)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 (Amazon Bedrock)","type":"chat"},{"id":"amazon/amazon.nova-pro-v1:0@us","name":"Nova Pro (US)","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.8,"output":3.2,"cache_read":0.2},"canonical_model_id":"amazon/nova-pro","display_name":"Nova Pro (US)","type":"chat"},{"id":"amazon/mistral.pixtral-large-2502-v1:0@us","name":"Pixtral Large (25.02) (Amazon Bedrock, US)","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-08","last_updated":"2025-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2,"output":6},"canonical_model_id":"mistral/pixtral-large-2502","display_name":"Pixtral Large (25.02) (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/zai.glm-4.7-flash","name":"GLM-4.7-Flash (Amazon Bedrock)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131072},"cost":{"input":0.07,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash (Amazon Bedrock)","type":"chat"},{"id":"amazon/moonshot.kimi-k2-thinking","name":"Kimi K2 Thinking (Amazon Bedrock)","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":262144},"cost":{"input":0.6,"output":2.5},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking (Amazon Bedrock)","type":"chat"},{"id":"amazon/google.gemma-3-4b-it@us","name":"Gemma 3 4B IT (Amazon Bedrock, US)","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.04,"output":0.08},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B IT (Amazon Bedrock, US)","type":"chat"},{"id":"amazon/mistral.voxtral-mini-3b-2507","name":"Voxtral Mini 3B 2507 (Amazon Bedrock)","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.04,"output":0.04},"canonical_model_id":"mistral/voxtral-mini-3b-2507","display_name":"Voxtral Mini 3B 2507 (Amazon Bedrock)","type":"chat"},{"id":"ovhcloud/gpt-oss-20b","name":"GPT OSS 20B (OVHcloud)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.18},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B (OVHcloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ovhcloud/gpt-oss-120b","name":"GPT OSS 120B (OVHcloud)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.09,"output":0.47},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (OVHcloud)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks_ai/gpt-oss-120b","name":"GPT OSS 120B (Fireworks AI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.014},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Fireworks AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks_ai/accounts/fireworks/models/inkling","name":"Inkling (Fireworks AI)","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling (Fireworks AI)","type":"chat"},{"id":"fireworks_ai/accounts/fireworks/models/gpt-oss-120b","name":"GPT OSS 120B (Fireworks AI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B (Fireworks AI)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fireworks_ai/accounts/fireworks/models/muse-spark-open","name":"Muse Spark Open (Fireworks AI)","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open (Fireworks AI)","type":"chat"},{"id":"mistral/codestral-latest","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"canonical_model_id":"mistral/codestral-latest","display_name":"Codestral (latest)","type":"chat"},{"id":"mistral/mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"mistral/mistral-large-latest","display_name":"Mistral Large (latest)","type":"chat"},{"id":"mistral/mistral-small-latest","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"mistral/mistral-small-latest","display_name":"Mistral Small (latest)","type":"chat"},{"id":"mistral/ministral-8b-2512","name":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.15,"output":0.15,"cache_read":0.015},"canonical_model_id":"mistral/ministral-8b-2512","display_name":"Ministral 3 8B 2512","type":"chat"},{"id":"mistral/devstral-medium-latest","name":"Devstral 2 (latest)","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/devstral-medium-latest","display_name":"Devstral 2 (latest)","type":"chat"},{"id":"mistral/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2,"cache_read":0.04},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"mistral/mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/mistral-medium-2505","display_name":"Mistral Medium 3","type":"chat"},{"id":"mistral/magistral-medium-latest","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"mistral/magistral-medium-latest","display_name":"Magistral Medium (latest)","type":"chat"},{"id":"mistral/mistral-medium-3-5","name":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":209715},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"mistral/mistral-medium-3-5","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"mistral/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"mistral/mistral-medium-3","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":104857},"cost":{"input":0.4,"output":2,"cache_read":0.04},"canonical_model_id":"mistral/mistral-medium-3","display_name":"Mistral Medium 3","type":"chat"},{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"mistral/mistral-large-2407","name":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-03-31","release_date":"2024-11-19","last_updated":"2024-11-19","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":104857},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"mistral/mistral-large-2407","display_name":"Mistral Large 2407","type":"chat"},{"id":"mistral/ministral-14b-2512","name":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"canonical_model_id":"mistral/ministral-14b-2512","display_name":"Ministral 3 14B 2512","type":"chat"},{"id":"mistral/voxtral-small-latest","name":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"canonical_model_id":"mistral/voxtral-small-latest","display_name":"Voxtral Small (latest)","type":"chat"},{"id":"mistral/ministral-3b-2512","name":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":104857},"cost":{"input":0.1,"output":0.1,"cache_read":0.01},"canonical_model_id":"mistral/ministral-3b-2512","display_name":"Ministral 3 3B 2512","type":"chat"},{"id":"mistral/mistral-medium-2604","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"mistral/codestral-2508","name":"Codestral 25.08","description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 25.08","type":"chat"},{"id":"mistral/mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"mistral/mistral-medium-latest","display_name":"Mistral Medium (latest)","type":"chat"},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 (Alibaba)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (Alibaba)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4,"cache_read":0.32},"canonical_model_id":"alibaba/qwen-max","display_name":"Qwen Max","type":"chat"},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash (Alibaba)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (Alibaba)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","type":"chat"},{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen/qwen-mt-plus","name":"Qwen MT Plus","description":"Flagship Qwen translation model with terminology control and support for 92 languages","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-24","last_updated":"2025-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":8192},"cost":{"input":2.46,"output":7.37},"canonical_model_id":"alibaba/qwen-mt-plus","display_name":"Qwen MT Plus","type":"chat"},{"id":"qwen/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813 (Alibaba)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.066},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (Alibaba)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max-0902","display_name":"Qwen3.8 Max 0902","type":"chat"},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5-turbo","type":"chat"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"canonical_model_id":"openai/gpt-5.2-pro","display_name":"GPT-5.2 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":8192},"cost":{"input":30,"output":60},"canonical_model_id":"openai/gpt-4","display_name":"GPT-4","type":"chat"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"canonical_model_id":"openai/o1","display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-latest","name":"GPT Latest (GPT-6 Astra)","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT Latest (GPT-6 Astra)","type":"chat"},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-08-06","display_name":"GPT-4o (2024-08-06)","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","pdf","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"canonical_model_id":"openai/o3-pro","display_name":"o3-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o-2024-11-20","display_name":"GPT-4o (2024-11-20)","type":"chat"},{"id":"openai/gpt-mini-latest","name":"GPT Mini Latest (GPT-5.6 Luna)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT Mini Latest (GPT-5.6 Luna)","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":150,"output":600},"canonical_model_id":"openai/o1-pro","display_name":"o1-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-pro-latest","name":"GPT Pro Latest (GPT-5.6 Sol)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT Pro Latest (GPT-5.6 Sol)","type":"chat"},{"id":"infomaniak/mistralai/Ministral-3-14B-Instruct-2512","name":"Ministral 3 14B (Infomaniak)","description":"Open vision-language model for efficient local deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"output":262144},"cost":{"input":0.33759,"output":0.45012},"canonical_model_id":"mistral/ministral-3-14b-instruct-2512","display_name":"Ministral 3 14B (Infomaniak)","type":"chat"},{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"stepfun":{"id":"stepfun","api":"https://api.stepfun.com/v1","name":"StepFun (China)","doc":"https://platform.stepfun.com/docs/zh/overview/concept","display_name":"StepFun (China)","models":[{"id":"step-1-32k","name":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":2.05,"output":9.59,"cache_read":0.41},"display_name":"Step 1 (32K)","type":"chat"},{"id":"step-tts-2","name":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-03-01","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Step TTS 2","type":"chat"},{"id":"step-5-preview","name":"Step 5 Preview","description":"StepFun frontier model for large-scale agent applications, coding, and knowledge work","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":0.96,"output":2.74,"cache_read":0.048},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","metadata":{"source":"public-provider-conf-template","lifecycle":"preview","notes":["Official maximum input and output are both 1M tokens and max_tokens defaults to INF; 384000 is recorded as a conservative default output ceiling.","Output tokens include both the reasoning process and the final answer; cache-miss input billing includes writing new content to the cache.","China list prices are CNY 7 input (cache miss), CNY 0.35 cache hit, and CNY 20 output per 1M tokens, converted to USD at 7.3 CNY/USD."]},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["low","medium","high"],"mode":"effort","effort":"medium"}},"temperature":true,"type":"chat","vision":true},{"id":"step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"display_name":"Step 3.5 Flash 2603","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-2-16k","name":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":5.21,"output":16.44,"cache_read":1.04},"display_name":"Step 2 (16K)","type":"chat"},{"id":"stepaudio-2.5-tts","name":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"StepAudio 2.5 TTS","type":"chat"},{"id":"stepaudio-2.5-asr","name":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"step","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-24","last_updated":"2026-07-02","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"StepAudio 2.5 ASR","type":"chat"},{"id":"step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"display_name":"Step 3.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-06-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.185,"output":1.11,"cache_read":0.037},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"}]},"hpc-ai":{"id":"hpc-ai","api":"https://api.hpc-ai.com/inference/v1","name":"HPC-AI","doc":"https://www.hpc-ai.com/doc/docs/quickstart/","display_name":"HPC-AI","models":[{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1002000,"output":128000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.6,"output":3,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5.1","name":"GLM 5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202000,"output":202000},"cost":{"input":0.615,"output":2.46,"cache_read":0.133},"display_name":"GLM 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196000,"output":195000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}}]},"tencent-coding-plan":{"id":"tencent-coding-plan","api":"https://api.lkeap.cloud.tencent.com/coding/v3","name":"Tencent Coding Plan (China)","doc":"https://cloud.tencent.com/document/product/1772/128947","display_name":"Tencent Coding Plan (China)","models":[{"id":"hunyuan-2.0-thinking","name":"Tencent HY 2.0 Think","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Tencent HY 2.0 Think","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hunyuan-2.0-instruct","name":"Tencent HY 2.0 Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Tencent HY 2.0 Instruct","type":"chat"},{"id":"kimi-k2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Kimi-K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"tc-code-latest","name":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Auto","type":"chat"},{"id":"hunyuan-turbos","name":"Hunyuan-TurboS","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Hunyuan-TurboS","type":"chat"},{"id":"hunyuan-t1","name":"Hunyuan-T1","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Hunyuan-T1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"sambanova":{"id":"sambanova","api":"https://api.sambanova.ai/v1","name":"SambaNova","doc":"https://docs.sambanova.ai/cloud/docs/get-started/supported-models","display_name":"SambaNova","models":[{"id":"DeepSeek-V3.1","name":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":7168},"cost":{"input":3,"output":4.5},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek-V3.1","type":"chat"},{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.6,"output":2.4,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Meta-Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":3072},"cost":{"input":0.6,"output":1.2},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"DeepSeek-V3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":7168},"cost":{"input":3,"output":4.5},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.38,"output":1.15},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.22,"output":0.59},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"tempr":{"id":"tempr","api":"https://api.temprhq.io/v1","name":"Tempr Gateway","doc":"https://temprhq.io/docs/gateway-reference.html","display_name":"Tempr Gateway","models":[{"id":"xiaomi-mimo/mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"xiaomi-mimo/mimo-v2.6-pro-ultraspeed","name":"MiMo-V2.6-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":4.35,"output":8.7,"cache_read":0.036},"canonical_model_id":"xiaomi/mimo-v2.6-pro-ultraspeed","display_name":"MiMo-V2.6-Pro-UltraSpeed","type":"chat"},{"id":"xiaomi-mimo/mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"cerebras/qwen-3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-09-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":40960},"cost":{"input":0.99,"output":1.49},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2026-06-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":40960},"cost":{"input":0.35,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/allam-2-7b","name":"ALLaM-2-7b","description":"ALLaM-2-7b instruction tuned model by SDAIA","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2025-01-23","last_updated":"2025-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0,"output":0},"canonical_model_id":"sdaia/allam-2-7b","display_name":"ALLaM-2-7b","type":"chat"},{"id":"groq/qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131042,"output":16384},"cost":{"input":0.8,"output":4},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"groq/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"groq/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-10-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.3,"output":0.9},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM-4.6V","type":"chat"},{"id":"zai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"zai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM-5V-Turbo","type":"chat"},{"id":"zai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-4.6v-flash","name":"GLM-4.6V-Flash","description":"Lightweight GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.6v-flash","display_name":"GLM-4.6V-Flash","type":"chat"},{"id":"zai/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16384},"cost":{"input":0.6,"output":1.8},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM-4.5V","type":"chat"},{"id":"zai/glm-5.3-flashx","name":"GLM-5.3-FlashX","description":"High-speed GLM-5.3-Flash serving option for coding and agent workflows","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-FlashX","type":"chat"},{"id":"zai/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai/glm-4.5-flash","name":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5-flash","display_name":"GLM-4.5-Flash","type":"chat"},{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7-flashx","display_name":"GLM-4.7-FlashX","type":"chat"},{"id":"zai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5-Air","type":"chat"},{"id":"zai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek/deepseek-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.6,"reasoning":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"reasoning":1.98,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-flash-latest","display_name":"Gemini Flash Latest","type":"chat"},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-flash-lite-latest","display_name":"Gemini Flash-Lite Latest","type":"chat"},{"id":"google/gemini-embedding-2","name":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1},"cost":{"input":0.2,"output":0},"canonical_model_id":"google/gemini-embedding-2","display_name":"Gemini Embedding 2","type":"embedding"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":1},"cost":{"input":0.15,"output":0},"canonical_model_id":"google/gemini-embedding-001","display_name":"Gemini Embedding 001","type":"embedding"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistral/mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-latest","display_name":"Mistral Large (latest)","type":"chat"},{"id":"mistral/mistral-small-latest","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"mistral/mistral-small-latest","display_name":"Mistral Small (latest)","type":"chat"},{"id":"mistral/zai-glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"status":"beta","cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"mistral/mistral-embed","name":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":3072},"cost":{"input":0.1,"output":0},"canonical_model_id":"mistral/mistral-embed","display_name":"Mistral Embed","type":"chat"},{"id":"mistral/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"mistral/voxtral-small-latest","name":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/voxtral-small-latest","display_name":"Voxtral Small (latest)","type":"chat"},{"id":"mistral/zai-glm-5-3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"mistral/mistral-medium-2604","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"mistral/mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"mistral/mistral-medium-latest","display_name":"Mistral Medium (latest)","type":"chat"},{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"inception":{"id":"inception","api":"https://api.inceptionlabs.ai/v1/","name":"Inception","doc":"https://docs.inceptionlabs.ai/get-started/models","display_name":"Inception","models":[{"id":"mercury-edit-2","name":"Mercury Edit 2","description":"Code editing dLLM for autocomplete (FIM) and next-edit suggestions","family":"mercury","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"display_name":"Mercury Edit 2","type":"chat"},{"id":"mercury-2.5","name":"Mercury 2.5","description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-11-01","release_date":"2026-09-08","last_updated":"2026-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":260000,"output":65536},"cost":{"input":0.04,"output":0.15,"cache_read":0.004},"display_name":"Mercury 2.5","type":"chat"},{"id":"mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"display_name":"Mercury 2","type":"chat"}]},"modelis":{"id":"modelis","api":"https://modelishub.com/v1","name":"Modelis","doc":"https://modelishub.com/pricing","display_name":"Modelis","models":[{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","max"]},{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]},{"type":"toggle"}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.0983,"output":0.1966},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":3,"output":9},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.768,"output":3.072},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"opencode":{"id":"opencode","api":"https://opencode.ai/inference/openai/v1","name":"OpenCode","doc":"https://opencode.ai/v2/docs/console/models/","display_name":"OpenCode","models":[{"id":"ling-3.0-flash-fin-free","name":"Ling 3.0 Flash Fin Free","description":"Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-09-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"inclusionai/ling-3.0-flash-fin","display_name":"Ling 3.0 Flash Fin Free","type":"chat"},{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"fledge-alpha-free","name":"Fledge Alpha Free","description":"Free-tier preview reasoning model with text and image input and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-10-01","last_updated":"2026-10-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0},"display_name":"Fledge Alpha Free","type":"chat"},{"id":"qwen3.6-plus-free","name":"Qwen3.6 Plus Free","description":"Legacy model retained for compatibility with older integrations","family":"qwen-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Qwen3.6 Plus Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":30,"output":180,"cache_read":30},"display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mimo-v2-pro-free","name":"MiMo V2 Pro Free","description":"Legacy model retained for compatibility with older integrations","family":"mimo-pro-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"MiMo V2 Pro Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"muse-spark-1.2-contributor-free","name":"Muse Spark 1.2 Free","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2 Free","type":"chat"},{"id":"ling-3.1-flash-free","name":"Ling 3.1 Flash Free","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"inclusionai/ling-3.1-flash","display_name":"Ling 3.1 Flash Free","type":"chat"},{"id":"muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5-free","name":"GLM-5 Free","description":"Legacy model retained for compatibility with older integrations","family":"glm-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"GLM-5 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"trinity-large-preview-free","name":"Trinity Large Preview","description":"Legacy model retained for compatibility with older integrations","family":"trinity","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-01-27","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0},"canonical_model_id":"arcee-ai/trinity-large-preview","display_name":"Trinity Large Preview","type":"chat"},{"id":"gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":30,"output":180,"cache_read":30},"display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"longcat-2.5-preview-free","name":"LongCat 2.5 Preview Free","description":"Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window","family":"longcat","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-25","last_updated":"2026-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"meituan/longcat-2.5-preview","display_name":"LongCat 2.5 Preview Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"ling-3.0-tiny-free","name":"Ling-3.0-tiny Free","description":"Compact MoE model for responsive agents, instruction following, and multi-turn conversations","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0},"display_name":"Ling-3.0-tiny Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k2.5-free","name":"Kimi K2.5 Free","description":"Legacy model retained for compatibility with older integrations","family":"kimi-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Kimi K2.5 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.7-free","name":"GLM-4.7 Free","description":"Legacy model retained for compatibility with older integrations","family":"glm-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"GLM-4.7 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.6","name":"GLM-4.6","description":"Legacy model retained for compatibility with older integrations","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.6,"output":2.2,"cache_read":0.1},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"laguna-s-2.1-free","name":"Laguna S 2.1 Free","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"poolside/laguna-s-2.1","display_name":"Laguna S 2.1 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5-codex","name":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"display_name":"GPT-5 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3-coder","name":"Qwen3 Coder","description":"Legacy model retained for compatibility with older integrations","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.45,"output":1.8},"display_name":"Qwen3 Coder","type":"chat"},{"id":"mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":262144},"provider":{"npm":"@ai-sdk/mistral","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"minimax-m3-free","name":"MiniMax-M3 Free","description":"Legacy model retained for compatibility with older integrations","family":"minimax-m3-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"MiniMax-M3 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-plus","name":"Qwen3.5 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1,"output":3.2,"cache_read":0.2},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"exo-free","name":"Exo Free","description":"Free-tier preview reasoning model with text and image input and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"temperature":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0},"display_name":"Exo Free","type":"chat"},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Legacy model retained for compatibility with older integrations","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.4,"output":2.5,"cache_read":0.4},"display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m2.5-free","name":"MiniMax-M2.5 Free","description":"Legacy model retained for compatibility with older integrations","family":"minimax-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"MiniMax-M2.5 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cat-jam-free","name":"Cat Jam Free","description":"A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Cat Jam Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-spark","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex Spark","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ring-2.6-1t-free","name":"Ring 2.6 1T Free","description":"Legacy model retained for compatibility with older integrations","family":"ring-1t-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-06","release_date":"2026-05-08","last_updated":"2026-05-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":66000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0},"display_name":"Ring 2.6 1T Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.6,"output":3,"cache_read":0.08},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"longcat-2.0-free","name":"LongCat-2.0 Free","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"meituan/longcat-2.0","display_name":"LongCat-2.0 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-3-5-haiku","name":"Claude Haiku 3.5","description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07-31","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0.8,"output":4,"cache_read":0.08,"cache_write":1},"display_name":"Claude Haiku 3.5","type":"chat"},{"id":"hy3-preview-free","name":"Hy3 preview Free","description":"Legacy model retained for compatibility with older integrations","family":"hy3-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Hy3 preview Free","type":"chat"},{"id":"gemini-3-flash","name":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":0.5,"output":3,"cache_read":0.05},"display_name":"Gemini 3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"space-bunny-free","name":"Space Bunny Free","description":"Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-23","last_updated":"2026-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":524288,"output":524288},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Space Bunny Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"ll-alpha-free","name":"LL Alpha Free","description":"Best in class local model","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-06","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"LL Alpha Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"nemotron-3-super-free","name":"Nemotron 3 Super Free","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m2.1-free","name":"MiniMax-M2.1 Free","description":"Legacy model retained for compatibility with older integrations","family":"minimax-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"MiniMax-M2.1 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2.6-flash-free","name":"MiMo-V2.6-Flash Free","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3-pro","name":"Gemini 3 Pro","description":"Legacy model retained for compatibility with older integrations","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"display_name":"Gemini 3 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"nemotron-3-ultra-free","name":"Nemotron 3 Ultra Free","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-02","release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"display_name":"Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-4.7","name":"GLM-4.7","description":"Legacy model retained for compatibility with older integrations","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.6,"output":2.2,"cache_read":0.1},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":128000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mimo-v2.5-free","name":"MiMo V2.5 Free","description":"MiMo omni model for text, image, video, audio, and agents","family":"mimo-v2.5-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"MiMo V2.5 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-code","name":"Grok Code Fast 1","description":"Legacy model retained for compatibility with older integrations","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-20","last_updated":"2025-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Grok Code Fast 1","type":"chat"},{"id":"gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"ling-2.6-flash-free","name":"Ling 2.6 Flash Free","description":"Legacy model retained for compatibility with older integrations","family":"ling-flash-free","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":32800},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0},"display_name":"Ling 2.6 Flash Free","type":"chat"},{"id":"glm-5.3-flash-free","name":"GLM-5.3-Flash Free","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash-free","name":"DeepSeek V4 Flash Free","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hy3-free","name":"Hy3 Free","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hy3-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":190000,"input":192000,"output":64000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"tencent/hy3","display_name":"Hy3 Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nemotron-3.5-lightning-free","name":"Nemotron 3.5 Lightning Free","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nemotron-3.5-super-vl-free","name":"Nemotron 3.5 Super VL Free","description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","display_name":"Nemotron 3.5 Super VL Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2","name":"Kimi K2","description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.4,"output":2.5,"cache_read":0.4},"display_name":"Kimi K2","type":"chat"},{"id":"glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"mimo-v2-omni-free","name":"MiMo V2 Omni Free","description":"Legacy model retained for compatibility with older integrations","family":"mimo-omni-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"MiMo V2 Omni Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1,"output":2,"cache_read":0.2},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4.1-flash-free","name":"DeepSeek V4.1 Flash Free","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"beam-free","name":"Beam Free","description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-06-30","release_date":"2026-10-05","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"reflection/beam-1.0-501b-a23b","display_name":"Beam Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"ling-3.0-flash-free","name":"Ling-3.0-flash Free","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Ling-3.0-flash Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"north-mini-code-free","name":"North Mini Code Free","description":"Cohere coding model for practical software engineering and agentic edits","family":"north-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-09-23","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0},"canonical_model_id":"cohere/north-mini-code-1-0","display_name":"North Mini Code Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.74,"output":3.84,"cache_read":0.145},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"big-pickle","name":"Big Pickle","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"big-pickle","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-17","last_updated":"2025-10-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":160000,"output":32000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Big Pickle","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625},"display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mimo-v2-flash-free","name":"MiMo V2 Flash Free","description":"Legacy model retained for compatibility with older integrations","family":"mimo-flash-free","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"MiMo V2 Flash Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"GPT-5.1 Codex Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"step-5-preview-free","name":"Step 5 Preview Free","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview Free","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://opencode.ai/inference/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"minimax-m2.1","name":"MiniMax-M2.1","description":"Legacy model retained for compatibility with older integrations","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.1},"display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://opencode.ai/inference/google/v1beta"},"cost":{"input":2,"output":10,"cache_read":0.1,"input_audio":2},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"x-preview-f-free","name":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"status":"deprecated","provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Ox Alpha Free (Unlimited)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"muse-spark-1.3-contributor-free","name":"Muse Spark 1.3 Free","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.","family":"muse-free","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0,"output":0,"cache_read":0},"display_name":"Muse Spark 1.3 Free","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"kenari":{"id":"kenari","api":"https://kenari.id/v1","name":"Kenari","doc":"https://kenari.id/docs","display_name":"Kenari","models":[{"id":"gpt-5-4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"grok-4-5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":0,"output":0},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat"},{"id":"gemini-2-5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat"},{"id":"nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5-3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat"},{"id":"kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat"},{"id":"gpt-5-6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-2-5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat"},{"id":"mimo-v2-5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"grok-build-0-1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4-7-flash:free","name":"GLM-4.7-Flash (Free)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash (Free)","type":"chat"},{"id":"gpt-image-2","name":"GPT-Image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":272000,"output":16384},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-image-2","display_name":"GPT-Image-2","type":"image-generation"},{"id":"qwen3-8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat"},{"id":"minimax-m2-7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat"},{"id":"grok-imagine-image","name":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"open_weights":false,"limit":{"context":16000,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"xai/grok-imagine-image","display_name":"Grok Imagine Image","type":"chat"},{"id":"mimo-v2-5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat"},{"id":"nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat"},{"id":"step-3-7-flash:free","name":"Step 3.7 Flash (Free)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0,"output":0},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash (Free)","type":"chat"},{"id":"kimi-k2-6:free","name":"Kimi K2.6 (Free)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (Free)","type":"chat"},{"id":"gpt-5-6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nano-banana-pro","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","type":"chat"},{"id":"gemini-3-1-pro","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat"},{"id":"glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"nano-banana-2","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","type":"chat"},{"id":"mistral-large:free","name":"Mistral Large (Free)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"mistral/mistral-large-latest","display_name":"Mistral Large (Free)","type":"chat"},{"id":"mimo-v2-5:free","name":"MiMo-V2.5 (Free)","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5 (Free)","type":"chat"},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2-7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat"},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"hy3:free","name":"Hy3 (Free)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"tencent/hy3","display_name":"Hy3 (Free)","type":"chat"},{"id":"kimi-k2-6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat"},{"id":"mistral-medium-3-5:free","name":"Mistral Medium 3.5 (Free)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5 (Free)","type":"chat"},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0,"output":0},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"glm-5-3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat"},{"id":"qwen3-7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat"},{"id":"nano-banana-2-lite","name":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.1-flash-lite-image","display_name":"Nano Banana 2 Lite","type":"chat"},{"id":"gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat"},{"id":"hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5-1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat"},{"id":"nemotron-3-super-120b-a12b:free","name":"Nemotron 3 Super 120B A12B (Free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B (Free)","type":"chat"},{"id":"gpt-5-5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-imagine-image-2-0","name":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8000,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"xai/grok-imagine-image-2.0","display_name":"Grok Imagine Image 2.0","type":"chat"},{"id":"deepseek-v4-flash:free","name":"DeepSeek V4 Flash (Free)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash (Free)","type":"chat"},{"id":"grok-4-6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":0,"output":0},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat"},{"id":"whisper-large-v3-turbo","name":"Whisper Large v3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":448},"cost":{"input":0,"output":0},"canonical_model_id":"openai/whisper-large-v3-turbo","display_name":"Whisper Large v3 Turbo","type":"chat"},{"id":"gemini-3-6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat"},{"id":"gemini-3-1-flash-tts","name":"Gemini 3.1 Flash TTS Preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","family":"gemini-flash","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.1-flash-tts-preview","display_name":"Gemini 3.1 Flash TTS Preview","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"kimi-k2-7-code:free","name":"Kimi K2.7 Code (Free)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code (Free)","type":"chat"},{"id":"gemini-3-5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat"},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"step-3-7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0,"output":0},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"kimi-code-plan-global":{"id":"kimi-code-plan-global","api":"https://api.kimi.ai/coding/v1","name":"Kimi For Coding (kimi.ai)","doc":"https://www.kimi.ai/code/docs/en/kimi-code/models.html","display_name":"Kimi For Coding (kimi.ai)","models":[{"id":"kimi-for-coding-highspeed","name":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi For Coding HighSpeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-for-coding","name":"kimi-for-coding","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.8-preview","display_name":"kimi-for-coding","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"k3-256k","name":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3-256K","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"trustedrouter":{"id":"trustedrouter","api":"https://api.trustedrouter.com/v1","name":"TrustedRouter","doc":"https://trustedrouter.com/docs","display_name":"TrustedRouter","models":[{"id":"trustedrouter/cheap","name":"Cheap","description":"TrustedRouter low-cost routing alias that prefers inexpensive healthy model endpoints.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"display_name":"Cheap","type":"chat"},{"id":"trustedrouter/synth-code","name":"Synth Code","description":"TrustedRouter code synthesis orchestration alias that combines multiple model responses into one answer.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-20","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"display_name":"Synth Code","type":"chat"},{"id":"trustedrouter/e2e","name":"End-to-End Encrypted","description":"TrustedRouter privacy routing alias for end-to-end encrypted provider routes where available.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"display_name":"End-to-End Encrypted","type":"chat"},{"id":"trustedrouter/zdr","name":"Zero Data Retention","description":"TrustedRouter privacy routing alias that prefers zero data retention model endpoints.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"display_name":"Zero Data Retention","type":"chat"},{"id":"trustedrouter/fast","name":"Fast","description":"TrustedRouter speed routing alias that prefers low-latency healthy model endpoints.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"display_name":"Fast","type":"chat"},{"id":"trustedrouter/synth","name":"Synth","description":"TrustedRouter synthesis orchestration alias that combines multiple model responses into one answer.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-20","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"display_name":"Synth","type":"chat"},{"id":"trustedrouter/auto","name":"Auto","description":"TrustedRouter automatic routing alias that chooses a healthy supported model endpoint for the request.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"display_name":"Auto","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"wafer.ai":{"id":"wafer.ai","api":"https://pass.wafer.ai/v1","name":"Wafer","doc":"https://docs.wafer.ai/wafer-pass","display_name":"Wafer","models":[{"id":"Kimi-K2.6","name":"Kimi K2.6","description":"Kimi K2.6 sparse MoE model with a 262K context window. Available serverless and not included in standard Wafer Pass. Non-ZDR only: requests with `Wafer-ZDR: required` are rejected.","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":1.14,"output":4.8,"cache_read":0.19,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.33,"output":1.32,"cache_read":0.07,"cache_write":0,"tiers":[{"input":0.66,"output":2.64,"cache_read":0.13,"cache_write":0,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.66,"output":2.64,"cache_read":0.13,"cache_write":0}},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"GLM-5.1","name":"GLM-5.1","description":"General Language Model 5.1 — high-quality bilingual (EN/ZH) generation with strong coding and reasoning capabilities.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-07","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.1,"cache_write":0},"display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.2,"output":4.1,"cache_read":0.2,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm5.2-fast","name":"GLM5.2-Fast","description":"The same model served for high TPS.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":10.25,"cache_read":0.5,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM5.2-Fast","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"zhipuai":{"id":"zhipuai","api":"https://open.bigmodel.cn/api/paas/v4","name":"Zhipu AI","doc":"https://docs.z.ai/guides/overview/pricing","display_name":"Zhipu AI","models":[{"id":"glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":5,"output":22,"cache_read":1.2,"cache_write":0},"display_name":"GLM-5V-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flashx","name":"GLM-5.3-FlashX","description":"High-speed GLM-5.3-Flash serving option for coding and agent workflows","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-09-18","last_updated":"2026-09-18","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-FlashX","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"display_name":"GLM-4.5-Air","type":"chat"},{"id":"glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"display_name":"GLM-4.7-FlashX","type":"chat"},{"id":"glm-4.5-flash","name":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.5-Flash","type":"chat"},{"id":"glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"display_name":"GLM-4.5V","type":"chat"},{"id":"glm-4.6v-flash","name":"GLM-4.6V-Flash","description":"Lightweight GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.6v-flash","display_name":"GLM-4.6V-Flash","type":"chat"},{"id":"glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"display_name":"GLM-4.5","type":"chat"},{"id":"glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"display_name":"GLM-4.6V","type":"chat"}]},"lynkr":{"id":"lynkr","api":"http://127.0.0.1:8081/v1","name":"Lynkr","doc":"https://github.com/Fast-Editor/Lynkr","display_name":"Lynkr","models":[{"id":"lynkr-auto","name":"Lynkr Auto (complexity routing)","description":"Virtual model: Lynkr scores each request on complexity and routes it to the tier model the user configured (local Ollama/llama.cpp for simple requests, configured cloud providers for complex ones).","family":"auto","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2026-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"display_name":"Lynkr Auto (complexity routing)","type":"chat"}]},"meganova":{"id":"meganova","api":"https://api.meganova.ai/v1","name":"Meganova","doc":"https://docs.meganova.ai","display_name":"Meganova","models":[{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.1,"output":0.3},"display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"XiaomiMiMo/MiMo-V2-Flash","name":"MiMo V2 Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32000},"cost":{"input":0.1,"output":0.3},"display_name":"MiMo V2 Flash","type":"chat"},{"id":"Qwen/Qwen3.5-Plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02","last_updated":"2026-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4,"reasoning":2.4},"display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.09,"output":0.6},"display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen2.5 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.2,"output":0.6},"display_name":"Qwen2.5 VL 32B Instruct","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-25","last_updated":"2025-08-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":1},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":164000},"cost":{"input":0.26,"output":0.38},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":64000},"cost":{"input":0.5,"output":2.15},"display_name":"DeepSeek R1 0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.25,"output":0.88},"display_name":"DeepSeek V3 0324","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-10","last_updated":"2025-10-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":0.4},"display_name":"DeepSeek V3.2 Exp","type":"chat"},{"id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.28,"output":1.2},"display_name":"MiniMax M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"display_name":"MiniMax M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral Nemo Instruct 2407","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.02,"output":0.04},"display_name":"Mistral Nemo Instruct 2407","type":"chat"},{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral Small 3.2 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Mistral Small 3.2 24B Instruct","type":"chat"},{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":2.8},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.6},"display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.2,"output":0.8},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.8,"output":2.56},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.45,"output":1.9},"display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"ovhcloud":{"id":"ovhcloud","api":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","name":"OVHcloud AI Endpoints","doc":"https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//","display_name":"OVHcloud AI Endpoints","models":[{"id":"qwen3.8-27b","name":"Qwen3.8-27B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.47,"output":3.19},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8-27B","type":"chat"},{"id":"qwen3guard-gen-8b","name":"Qwen3Guard-Gen-8B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"display_name":"Qwen3Guard-Gen-8B","type":"chat"},{"id":"qwen3guard-gen-0.6b","name":"Qwen3Guard-Gen-0.6B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"display_name":"Qwen3Guard-Gen-0.6B","type":"chat"},{"id":"gpt-oss-20b","name":"gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.18},"display_name":"gpt-oss-20b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-9b","name":"Qwen3.5-9B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.12,"output":0.18},"display_name":"Qwen3.5-9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta-llama-3_3-70b-instruct","name":"Meta-Llama-3_3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-01","last_updated":"2025-04-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.74,"output":0.74},"display_name":"Meta-Llama-3_3-70B-Instruct","type":"chat"},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-18","last_updated":"2026-05-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.71,"output":4.25},"display_name":"Qwen3.5-397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen2.5-vl-72b-instruct","name":"Qwen2.5-VL-72B-Instruct","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":1.01,"output":1.01},"display_name":"Qwen2.5-VL-72B-Instruct","type":"chat"},{"id":"qwen3.6-27b","name":"Qwen3.6-27B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.47,"output":3.19},"display_name":"Qwen3.6-27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistral-small-3.2-24b-instruct-2506","name":"Mistral-Small-3.2-24B-Instruct-2506","description":"Efficient Mistral model for fast chat, extraction, and production assistants","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-16","last_updated":"2025-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.31},"display_name":"Mistral-Small-3.2-24B-Instruct-2506","type":"chat"},{"id":"gpt-oss-120b","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.09,"output":0.47},"display_name":"gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-nemo-instruct-2407","name":"Mistral-Nemo-Instruct-2407","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.14,"output":0.14},"display_name":"Mistral-Nemo-Instruct-2407","type":"chat"}]},"requesty":{"id":"requesty","api":"https://router.requesty.ai/v1","name":"Requesty","doc":"https://requesty.ai/solution/llm-routing/models","display_name":"Requesty","models":[{"id":"ring-2.6-1t","name":"ring-2.6-1t","description":"Inclusion AI ring-2.6-1t","family":"ring","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-05-08","last_updated":"2026-05-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":2.5},"display_name":"ring-2.6-1t","type":"chat"},{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.75,"output":16.5,"cache_read":0.275},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"nemotron-3-ultra-nvfp4","name":"nemotron-3-ultra-nvfp4","description":"Nemotron-3-Ultra-550B-A55B-NVFP4 is a frontier-scale large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for the most demanding workloads, including complex multi-step agents, long-context analysis, and high-accuracy reasoning over code, math, and science. The model employs a hybrid Latent Mixture-of-Experts (LatentMoE) architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. Like the Super model, the Ultra model incorporates Multi-Token Prediction (MTP) layers for faster text generation and improved quality, and it is trained using an NVFP4 pre-training recipe to maximize compute efficiency. The model has 55B active parameters and 550B parameters in total.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"display_name":"nemotron-3-ultra-nvfp4","type":"chat"},{"id":"gpt-6.1-sol@eu","name":"GPT-6.1 Sol (EU)","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.4,"output":12,"cache_read":0.12,"cache_write":3,"tiers":[{"input":4.8,"output":18,"cache_read":0.24,"cache_write":6,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.8,"output":18,"cache_read":0.24,"cache_write":6}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol (EU)","type":"chat"},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":30},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5@eu","name":"Claude Opus 5 (EU)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (EU)","type":"chat"},{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.43,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"ling-2.6-1t","name":"ling-2.6-1t","description":"Inclusion AI ling-2.6-1t","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":2.5},"display_name":"ling-2.6-1t","type":"chat"},{"id":"claude-haiku-5-5@eu","name":"Claude Haiku 5.5 (EU)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.11,"output":0.55,"cache_read":0.02,"cache_write":0.14,"tiers":[{"input":0.55,"output":2.75,"cache_read":0.06,"cache_write":0.69,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (EU)","type":"chat"},{"id":"gpt-4o-mini@eu","name":"GPT-4o mini (EU)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.165,"output":0.66,"cache_read":0.0825},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini (EU)","type":"chat"},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":2.5,"output":7.5,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3.5-lightning-30b-a3b","name":"nemotron-3.5-lightning-30b-a3b","description":"NVIDIA Nemotron 3.5 Lightning 30B-A3B is a hybrid Mamba-2 + MoE + Attention model with 30B total and 3B active parameters, pre-trained on over 20T tokens with an NVFP4 recipe and Multi-Token Prediction for fast generation. Up to 1M token context for long-running autonomous agents, sub-agent workhorse deployments, and agentic workflows. Supports reasoning and tool calling. English and coding languages plus Spanish, French, German, Italian, and Japanese. Open weights under the OpenMDW License Agreement v1.1. Part of the NVIDIA Nemotron family.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"display_name":"nemotron-3.5-lightning-30b-a3b","type":"chat"},{"id":"mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"mistral-medium-3-5@eu","name":"Mistral Medium 3.5 (EU)","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.65,"output":8.25,"cache_read":1.65},"canonical_model_id":"mistral/mistral-medium-3-5","display_name":"Mistral Medium 3.5 (EU)","type":"chat"},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5@eu","name":"GPT-5 (EU)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.375,"output":11,"cache_read":0.1375},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5 (EU)","type":"chat"},{"id":"kimi-k2.5@eu","name":"Kimi K2.5 (EU)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16000},"cost":{"input":0.72,"output":3.6,"cache_read":0.72,"cache_write":0.72},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5 (EU)","type":"chat"},{"id":"deepseek-v4-flash-0731@eu","name":"DeepSeek V4 Flash 0731 (EU)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.28,"output":0.56,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731 (EU)","type":"chat"},{"id":"seed-2.0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":3,"cache_read":0.1},"canonical_model_id":"bytedance-seed/seed-2.0-pro","display_name":"Seed 2.0 Pro","type":"chat"},{"id":"kimi-k3@eu","name":"Kimi K3 (EU)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":3,"output":15,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (EU)","type":"chat"},{"id":"seed-1.8","name":"seed-1.8","description":"Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"seed-1.8","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"cost":{"input":0.2,"output":0.6,"cache_read":0.07},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.26,"output":2.6},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistral-medium-latest@eu","name":"Mistral Medium (latest) (EU)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.44,"output":2.2,"cache_read":0.44},"canonical_model_id":"mistral/mistral-medium-latest","display_name":"Mistral Medium (latest) (EU)","type":"chat"},{"id":"glm-5.2-fast","name":"glm-5.2-fast","description":"GLM-5.2 introduces a robust 1M-token context and advanced, multi-effort coding capabilities to significantly enhance performance on long-horizon tasks. Its new IndexShare architecture and improved MTP layer simultaneously boost efficiency by reducing per-token FLOPs and increasing speculative decoding lengths. A 743B-parameter model in Zhipu AI's GLM series, designed to plan, execute, and iterate autonomously on extended, engineering-grade tasks.","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-07-13","last_updated":"2026-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.1,"output":6.6,"cache_read":0.21},"display_name":"glm-5.2-fast","type":"chat"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.28,"output":0.56,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-pro-0813@eu","name":"DeepSeek V4 Pro 0813 (EU)","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":1.75,"output":3.5,"cache_read":0.44},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813 (EU)","type":"chat"},{"id":"inkling-256k","name":"inkling-256k","description":"Inkling 256K is the extended context variant of Inkling, a large MoE hybrid reasoning model from Thinking Machines with audio and vision input support and a 256K context window.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":1.87,"output":4.68,"cache_read":0.374},"display_name":"inkling-256k","type":"chat"},{"id":"muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":20480},"cost":{"input":0,"output":0},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat"},{"id":"claude-opus-4-8@eu","name":"Claude Opus 4.8 (EU)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":3,"output":15,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-fable-5@eu","name":"Claude Fable 5 (EU)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"nemotron-3-nano-omni@eu","name":"nemotron-3-nano-omni@eu","description":"The most open, efficient, and accurate omni modal reasoning model for agentic AI.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-20","last_updated":"2026-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":300000},"cost":{"input":0.06,"output":0.24,"cache_read":0.06},"display_name":"nemotron-3-nano-omni@eu","type":"chat"},{"id":"gpt-4.1@eu","name":"GPT-4.1 (EU)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2.2,"output":8.8,"cache_read":0.55},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1 (EU)","type":"chat"},{"id":"gemini-3.1-flash-lite@eu","name":"Gemini 3.1 Flash Lite (EU)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.275,"output":1.65,"cache_read":0.0275,"cache_write":0.091663},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite (EU)","type":"chat"},{"id":"nvidia-nemotron-3-super-120b-a12b","name":"nvidia-nemotron-3-super-120b-a12b","description":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.5},"display_name":"nvidia-nemotron-3-super-120b-a12b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":524288},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"gemini-3.5-flash-lite@eu","name":"Gemini 3.5 Flash Lite (EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.33,"output":2.75,"cache_read":0.033},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite (EU)","type":"chat"},{"id":"deepseek-v4.1-flash-1017@eu","name":"DeepSeek V4.1 Flash 1017 (EU)","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017 (EU)","type":"chat"},{"id":"claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"kimi-k2.7-code@eu","name":"Kimi K2.7 Code (EU)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.25,"output":4.5,"cache_read":0.31},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code (EU)","type":"chat"},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.1@eu","name":"GLM-5.1 (EU)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":200000},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1 (EU)","type":"chat"},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-haiku-4-5@eu","name":"Claude Haiku 4.5 (latest) (EU)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest) (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-4-5@eu","name":"Claude Sonnet 4.5 (latest) (EU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.3,"cache_write":4.125,"tiers":[{"input":6.6,"output":24.75,"cache_read":0.6,"cache_write":8.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6.6,"output":24.75,"cache_read":0.6,"cache_write":8.25}},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest) (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"laguna-xs.2","name":"Laguna XS.2","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"poolside/laguna-xs.2","display_name":"Laguna XS.2","type":"chat"},{"id":"leanstral-1-5@eu","name":"leanstral-1-5@eu","description":"Leanstral 1.5 is an updated Lean 4 formal proof engineering model from Mistral AI, optimized for automated theorem proving and autoformalization. It has 119B total parameters with 6.5B active and supports a 256K token context window. It supports native function calling and structured output.","family":"leanstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"display_name":"leanstral-1-5@eu","type":"chat"},{"id":"claude-sonnet-5-5@eu","name":"Claude Sonnet 5.5 (EU)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 (EU)","type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-sonnet-4-6@eu","name":"Claude Sonnet 4.6 (EU)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.3,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.5,"output":7,"cache_read":0.15},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5.5@eu","name":"GPT-5.5 (EU)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5.5,"output":33,"cache_read":0.55,"tiers":[{"input":11,"output":49.5,"cache_read":1.1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":11,"output":49.5,"cache_read":1.1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5 (EU)","type":"chat"},{"id":"ling-3.0-tiny","name":"ling-3.0-tiny","description":"Ling-3.0-tiny is an efficient 7.9B parameter MoE model from inclusionAI with only 1.3B active parameters per token. Built for responsive agents, reliable instruction following and multi turn conversation, with a 256K context window, native function calling, prompt caching and switchable Thinking and Instant modes.","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"display_name":"ling-3.0-tiny","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"step-5-preview","name":"Step 5 Preview","description":"StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-09-16","last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1,"output":2.7,"cache_read":0.05},"canonical_model_id":"stepfun/step-5-preview","display_name":"Step 5 Preview","type":"chat"},{"id":"claude-opus-5-5@eu","name":"Claude Opus 5.5 (EU)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (EU)","type":"chat"},{"id":"gemini-4-argon@eu","name":"Gemini 4 Argon (EU)","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2.2,"output":11,"cache_read":0.11},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon (EU)","type":"chat"},{"id":"gpt-5-mini@eu","name":"GPT-5 Mini (EU)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.275,"output":2.2,"cache_read":0.0275},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini (EU)","type":"chat"},{"id":"mistral-medium-3-5","name":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.65,"output":8.25,"cache_read":1.65},"canonical_model_id":"mistral/mistral-medium-3-5","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"cache_write":1.25,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"cache_write":2.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4,"cache_write":2.5}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":20480},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","display_name":"Nemotron 3 Nano Omni 30B A3B Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.07,"output":0.34,"cache_read":0.07},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4@eu","name":"GPT-5.4 (EU)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.75,"output":16.5,"cache_read":0.275,"tiers":[{"input":5.5,"output":24.75,"cache_read":0.55,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5.5,"output":24.75,"cache_read":0.55}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4 (EU)","type":"chat"},{"id":"claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1","display_name":"Claude Opus 4.1 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"grok-4.2-beta","name":"grok-4.2-beta","description":"Grok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":2,"output":6,"cache_read":0.2,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":0.4,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.4,"cache_write":4}},"display_name":"grok-4.2-beta","type":"chat"},{"id":"gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":2},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-lightning-3.5-30b-a3b","name":"nemotron-lightning-3.5-30b-a3b","description":"Nemotron-Lightning-3.5-30B-A3B is a 30B-parameter Mixture-of-Experts language model (3B active) from NVIDIA's Nemotron-H family, built on a hybrid Mamba-Transformer architecture for efficient long-context inference. Like other models in the family, it responds to queries by first generating a reasoning trace and then concluding with a final response, with reasoning behavior configurable through a flag in the chat template. It includes a multi-token prediction (MTP) speculative decoding head for low-latency serving.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-15","last_updated":"2026-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"display_name":"nemotron-lightning-3.5-30b-a3b","type":"chat"},{"id":"gpt-5-nano@eu","name":"GPT-5 Nano (EU)","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.055,"output":0.44,"cache_read":0.0055},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano (EU)","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":4.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":9,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":9}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":1,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1,"cache_write":4}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"seed-2.0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.1,"output":0.4,"cache_read":0.02},"canonical_model_id":"bytedance-seed/seed-2.0-mini","display_name":"Seed 2.0 Mini","type":"chat"},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.6@eu","name":"Kimi K2.6 (EU)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":128000},"cost":{"input":0.95,"output":4,"cache_read":0.95},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6 (EU)","type":"chat"},{"id":"qwen3.5-2b","name":"qwen3.5-2b","description":"Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languages, thinking/reasoning mode, and tool calling for agentic workflows. A strong choice for prototyping, fine-tuning, and efficient multilingual deployments.","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.02,"output":0.1},"display_name":"qwen3.5-2b","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"sakana/fugu-ultra","display_name":"Fugu Ultra","type":"chat"},{"id":"minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":1.2},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":1.583},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"ling-2.6-flash","name":"ling-2.6-flash","description":"Inclusion AI ling-2.6-flash","family":"ling","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.3},"display_name":"ling-2.6-flash","type":"chat"},{"id":"gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":4.5},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.7-flash@eu","name":"Gemini 3.7 Flash (EU)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.825,"output":4.125,"cache_read":0.0825},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-4.1-nano@eu","name":"GPT-4.1 nano (EU)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.11,"output":0.44,"cache_read":0.0275},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano (EU)","type":"chat"},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat"},{"id":"gpt-5.1@eu","name":"GPT-5.1 (EU)","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.375,"output":11,"cache_read":0.1375},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1 (EU)","type":"chat"},{"id":"gemini-2.5-flash-lite@eu","name":"Gemini 2.5 Flash-Lite (EU)","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.18333},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"nemotron-3-nano-omni","name":"nemotron-3-nano-omni","description":"The most open, efficient, and accurate omni modal reasoning model for agentic AI.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-20","last_updated":"2026-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":300000},"cost":{"input":0.06,"output":0.24,"cache_read":0.06},"display_name":"nemotron-3-nano-omni","type":"chat"},{"id":"claude-sonnet-4@eu","name":"Claude Sonnet 4 (latest) (EU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"canonical_model_id":"anthropic/claude-sonnet-4-0","display_name":"Claude Sonnet 4 (latest) (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":32768},"cost":{"input":1.87,"output":4.68,"cache_read":0.374},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0027},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v4.1-flash@eu","name":"DeepSeek V4.1 Flash (EU)","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash (EU)","type":"chat"},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.8-2.4T-A95B@eu","name":"Qwen3.8 2.4T A95B (EU)","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"cost":{"input":2.5,"output":6,"cache_read":0.63},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B (EU)","type":"chat"},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.16,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-flash-next","name":"Qwen3.8 Flash Next","description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.8-flash-next","display_name":"Qwen3.8 Flash Next","type":"chat"},{"id":"qwen3.8-flash-next@eu","name":"Qwen3.8 Flash Next (EU)","description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.8-flash-next","display_name":"Qwen3.8 Flash Next (EU)","type":"chat"},{"id":"mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.165,"output":0.66,"cache_read":0.165},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5.5,"output":33,"cache_read":0.55},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-5@eu","name":"Claude Sonnet 5 (EU)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (EU)","type":"chat"},{"id":"gemini-3.8-flash@eu","name":"Gemini 3.8 Flash (EU)","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.825,"output":4.125,"cache_read":0.0825},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.14,"output":1,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3@eu","name":"GLM-5.3 (EU)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.2,"output":4.2,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (EU)","type":"chat"},{"id":"gemini-2.5-flash@eu","name":"Gemini 2.5 Flash (EU)","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.55},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.8,"output":2.55,"cache_read":0.16},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2@eu","name":"GLM-5.2 (EU)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.2,"output":4.2,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2 (EU)","type":"chat"},{"id":"gpt-5.6-sol@eu","name":"GPT-5.6 Sol (EU)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5,"tiers":[{"input":8.8,"output":33,"cache_read":0.88,"cache_write":11,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8.8,"output":33,"cache_read":0.88,"cache_write":11}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol (EU)","type":"chat"},{"id":"seed-2.0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":3,"cache_read":0.1},"canonical_model_id":"bytedance-seed/seed-2.0-code","display_name":"Seed 2.0 Code","type":"chat"},{"id":"devstral-latest@eu","name":"devstral-latest@eu","description":"An enterprise grade text model, that excels at using tools to explore codebases, editing multiple files and power software engineering agents.","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.44,"output":2.2,"cache_read":0.44},"display_name":"devstral-latest@eu","type":"chat"},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-pro@eu","name":"Gemini 2.5 Pro (EU)","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.25,"output":10,"cache_read":0.31,"cache_write":2.375,"tiers":[{"input":2.5,"output":15,"cache_read":0.62,"cache_write":4.75,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.62,"cache_write":4.75}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5.6-terra@eu","name":"GPT-5.6 Terra (EU)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra (EU)","type":"chat"},{"id":"grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.1},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3-flash@eu","name":"GLM-5.3-Flash (EU)","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"cost":{"input":0.2,"output":0.6,"cache_read":0.07},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash (EU)","type":"chat"},{"id":"minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":1.2},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro@eu","name":"DeepSeek V4 Pro (EU)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.75,"output":3.5,"cache_read":0.44},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro (EU)","type":"chat"},{"id":"devstral-latest","name":"devstral-latest","description":"An enterprise grade text model, that excels at using tools to explore codebases, editing multiple files and power software engineering agents.","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.44,"output":2.2,"cache_read":0.44},"display_name":"devstral-latest","type":"chat"},{"id":"o4-mini@eu","name":"o4-mini (EU)","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.21,"output":4.84,"cache_read":0.3025},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini (EU)","type":"chat"},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.13,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.63,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"mistral-small-2603@eu","name":"Mistral Small 4 (EU)","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.165,"output":0.66,"cache_read":0.165},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4 (EU)","type":"chat"},{"id":"qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.5-flash@eu","name":"Gemini 3.5 Flash (EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.65,"output":9.9,"cache_read":0.165,"cache_write":1.7413},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"nvidia/nemotron-3.5-content-safety","display_name":"Nemotron 3.5 Content Safety","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"nvidia-nemotron-3-ultra","name":"nvidia-nemotron-3-ultra","description":"NVIDIA Nemotron 3 Ultra is NVIDIA's strongest open-weights reasoning model, positioned near GPT-5.4 Mini (xhigh) and ahead of DeepSeek V4-Flash and Qwen3.5-397B-A17B.","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":false,"structured_output":false,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":2.5},"display_name":"nvidia-nemotron-3-ultra","type":"chat"},{"id":"claude-fable-5.1@eu","name":"Claude Fable 5.1 (EU)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":0.275,"cache_write":13.75},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"gpt-6-luna@eu","name":"GPT-6 Luna (EU)","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.12,"output":0.6,"cache_read":0.012,"cache_write":0.15,"tiers":[{"input":0.24,"output":0.9,"cache_read":0.024,"cache_write":0.3,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.24,"output":0.9,"cache_read":0.024,"cache_write":0.3}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna (EU)","type":"chat"},{"id":"claude-opus-4-6@eu","name":"Claude Opus 4.6 (EU)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"muse-wonder-1.0","name":"Muse Wonder","description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":943718},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"meta/muse-wonder-1.0","display_name":"Muse Wonder","type":"chat"},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"leanstral-1-5","name":"leanstral-1-5","description":"Leanstral 1.5 is an updated Lean 4 formal proof engineering model from Mistral AI, optimized for automated theorem proving and autoformalization. It has 119B total parameters with 6.5B active and supports a 256K token context window. It supports native function calling and structured output.","family":"leanstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"display_name":"leanstral-1-5","type":"chat"},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.6-luna@eu","name":"GPT-5.6 Luna (EU)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"tiers":[{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna (EU)","type":"chat"},{"id":"claude-opus-4-7@eu","name":"Claude Opus 4.7 (EU)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"kat-coder-pro","name":"kat-coder-pro","description":"KAT-Coder-Pro V2 by KwaiKAT is a non-reasoning model optimized for agentic coding. It delivers strong performance on reasoning-style tasks while requiring significantly fewer output tokens than peer models. With the 1210 release, it achieved a score of 64 on the Artificial Analysis Intelligence Index, placing it in the global Top 10 and ranking first among all non-reasoning models.","family":"kat-coder","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":1.2},"display_name":"kat-coder-pro","type":"chat"},{"id":"laguna-m.1","name":"Laguna M.1","description":"Poolside's open-weight model for agentic coding and long-horizon work","family":"laguna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"poolside/laguna-m.1","display_name":"Laguna M.1","type":"chat"},{"id":"gpt-6-sol@eu","name":"GPT-6 Sol (EU)","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.4,"output":12,"cache_read":0.24,"cache_write":3,"tiers":[{"input":4.8,"output":18,"cache_read":0.48,"cache_write":6,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.8,"output":18,"cache_read":0.48,"cache_write":6}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol (EU)","type":"chat"},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.2,"output":4.2,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":1,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1,"cache_write":4}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-large-4@eu","name":"Mistral Large 4 (EU)","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":524288},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4 (EU)","type":"chat"},{"id":"minimax-m3@eu","name":"MiniMax-M3 (EU)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.4,"output":2,"cache_read":0.1},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3 (EU)","type":"chat"},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.32,"output":1.28,"cache_read":0.032,"cache_write":0.4},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-4.1-mini@eu","name":"GPT-4.1 mini (EU)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.44,"output":1.76,"cache_read":0.11},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini (EU)","type":"chat"},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-5@eu","name":"Claude Opus 4.5 (latest) (EU)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest) (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.28,"output":0.56,"cache_read":0.07},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.44,"output":2.2,"cache_read":0.44},"canonical_model_id":"mistral/mistral-medium-latest","display_name":"Mistral Medium (latest)","type":"chat"},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"mistral":{"id":"mistral","name":"Mistral","doc":"https://docs.mistral.ai/getting-started/models/","display_name":"Mistral","models":[{"id":"open-mistral-nemo","name":"Open Mistral Nemo","description":"Legacy model retained for compatibility with older integrations","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.15,"output":0.15},"display_name":"Open Mistral Nemo","type":"chat"},{"id":"codestral-latest","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"display_name":"Codestral (latest)","type":"chat"},{"id":"mistral-large-2411","name":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-18","last_updated":"2024-11-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"status":"deprecated","cost":{"input":2,"output":6},"canonical_model_id":"mistral/mistral-large-2411","display_name":"Mistral Large 2.1","type":"chat"},{"id":"mistral-nemo","name":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.15,"output":0.15},"display_name":"Mistral Nemo","type":"chat"},{"id":"voxtral-mini-tts-latest","name":"Voxtral Mini TTS (latest)","description":"Multilingual text-to-speech model with zero-shot voice cloning","family":"voxtral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Voxtral Mini TTS (latest)","type":"chat"},{"id":"mistral-medium-2508","name":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"display_name":"Mistral Medium 3.1","type":"chat"},{"id":"mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"display_name":"Mistral Large (latest)","type":"chat"},{"id":"mistral-small-latest","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Mistral Small (latest)","type":"chat"},{"id":"ministral-8b-2512","name":"Ministral 3 8B","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":0.15,"cache_read":0.015},"canonical_model_id":"mistral/ministral-3-8b-instruct-2512","display_name":"Ministral 3 8B","type":"chat"},{"id":"zai-glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"ministral-8b-latest","name":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.1,"output":0.1},"display_name":"Ministral 8B (latest)","type":"chat"},{"id":"devstral-medium-latest","name":"Devstral 2 (latest)","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"display_name":"Devstral 2 (latest)","type":"chat"},{"id":"mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":262144},"status":"beta","cost":{"input":0.68,"output":2.09,"cache_read":0.07},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"open-mixtral-8x22b","name":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mixtral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":64000},"status":"deprecated","cost":{"input":2,"output":6},"display_name":"Mixtral 8x22B","type":"chat"},{"id":"devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"display_name":"Devstral 2","type":"chat"},{"id":"mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0.4,"output":2},"display_name":"Mistral Medium 3","type":"chat"},{"id":"magistral-medium-latest","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"status":"deprecated","cost":{"input":2,"output":5},"display_name":"Magistral Medium (latest)","type":"chat"},{"id":"voxtral-small-2507","name":"Voxtral Small","description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"cost":{"input":0.1,"output":0.4},"display_name":"Voxtral Small","type":"chat"},{"id":"glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"labs-leanstral-1-5-1","name":"Leanstral 1.5","description":"An updated Lean 4 formal proof engineering model optimised for automated theorem proving and autoformalization. 119B total parameters, 6.5B active.","family":"leanstral","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Leanstral 1.5","type":"chat"},{"id":"pixtral-12b","name":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-01","last_updated":"2024-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.15,"output":0.15},"display_name":"Pixtral 12B","type":"chat"},{"id":"mistral-embed","name":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral-embed","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":3072},"cost":{"input":0.1,"output":0},"display_name":"Mistral Embed","type":"chat"},{"id":"devstral-small-2505","name":"Devstral Small 2505","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.1,"output":0.3},"display_name":"Devstral Small 2505","type":"chat"},{"id":"mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"display_name":"Mistral Small 4","type":"chat"},{"id":"devstral-medium-2507","name":"Devstral Medium","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.4,"output":2},"display_name":"Devstral Medium","type":"chat"},{"id":"voxtral-mini-latest","name":"Voxtral Mini (latest)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"voxtral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Voxtral Mini (latest)","type":"chat"},{"id":"labs-devstral-small-2512","name":"Devstral Small 2","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Devstral Small 2","type":"chat"},{"id":"mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"display_name":"Mistral Large 3","type":"chat"},{"id":"devstral-latest","name":"Devstral 2","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"display_name":"Devstral 2","type":"chat"},{"id":"ministral-14b-2512","name":"Ministral 3 14B","description":"Open vision-language model for efficient local deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"canonical_model_id":"mistral/ministral-3-14b-instruct-2512","display_name":"Ministral 3 14B","type":"chat"},{"id":"devstral-small-2507","name":"Devstral Small","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.1,"output":0.3},"display_name":"Devstral Small","type":"chat"},{"id":"pixtral-large-latest","name":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2024-11-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":2,"output":6},"display_name":"Pixtral Large (latest)","type":"chat"},{"id":"voxtral-small-latest","name":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"cost":{"input":0.1,"output":0.3},"display_name":"Voxtral Small (latest)","type":"chat"},{"id":"open-mixtral-8x7b","name":"Mixtral 8x7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mixtral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-01","release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"status":"deprecated","cost":{"input":0.7,"output":0.7},"display_name":"Mixtral 8x7B","type":"chat"},{"id":"mistral-small-2506","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":0.1,"output":0.3},"display_name":"Mistral Small 3.2","type":"chat"},{"id":"zai-glm-5-3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"ministral-3b-2512","name":"Ministral 3 3B","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":262144},"cost":{"input":0.1,"output":0.1,"cache_read":0.01},"canonical_model_id":"mistral/ministral-3-3b-instruct-2512","display_name":"Ministral 3 3B","type":"chat"},{"id":"mistral-medium-2604","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"display_name":"Mistral Medium 3.5","type":"chat"},{"id":"open-mistral-7b","name":"Mistral 7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-09-27","last_updated":"2023-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"status":"deprecated","cost":{"input":0.25,"output":0.25},"display_name":"Mistral 7B","type":"chat"},{"id":"codestral-2508","name":"Codestral 25.08","description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 25.08","type":"chat"},{"id":"ministral-3b-latest","name":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":128000},"cost":{"input":0.04,"output":0.04},"display_name":"Ministral 3B (latest)","type":"chat"},{"id":"mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"canonical_model_id":"mistral/mistral-medium-latest","display_name":"Mistral Medium (latest)","type":"chat"}]},"amazon-bedrock":{"id":"amazon-bedrock","name":"Amazon Bedrock","doc":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","display_name":"Amazon Bedrock","models":[{"id":"google.gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.09,"output":0.29},"canonical_model_id":"google/gemma-3-12b-it","display_name":"Gemma 3 12B IT","type":"chat"},{"id":"google.gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.04,"output":0.08},"canonical_model_id":"google/gemma-3-4b-it","display_name":"Gemma 3 4B IT","type":"chat"},{"id":"eu.anthropic.claude-fable-5","name":"Claude Fable 5 (EU)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"qwen.qwen3-coder-480b-a35b-v1:0","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.45,"output":1.8},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3-Coder 480B-A35B Instruct","type":"chat"},{"id":"google.gemma-4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":0.14,"output":0.4},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"us.writer.palmyra-x5-v1:0","name":"Palmyra X5 (US)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"palmyra","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1040000,"input":1040000,"output":8192},"cost":{"input":0.6,"output":6},"canonical_model_id":"writer/palmyra-x5","display_name":"Palmyra X5 (US)","type":"chat"},{"id":"google.gemma-4-e2b","name":"Gemma 4 E2B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":0.04,"output":0.08},"canonical_model_id":"google/gemma-4-E2B-it","display_name":"Gemma 4 E2B IT","type":"chat"},{"id":"us.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (US)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"global.openai.gpt-6-astra","name":"GPT-6 Astra (Global)","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"ultrafast":{"cost":{"input":60,"output":300,"cache_read":6,"cache_write":75},"provider":{"body":{"additionalModelRequestFields":{"service_tier":"ultrafast"}}}}}},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra (Global)","type":"chat"},{"id":"us.openai.gpt-6.1-sol","name":"GPT-6.1 Sol (US)","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"ultrafast":{"cost":{"input":13.2,"output":66,"cache_read":0.66,"cache_write":16.5},"provider":{"body":{"additionalModelRequestFields":{"service_tier":"ultrafast"}}}}}},"cost":{"input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75,"tiers":[{"input":4.4,"output":16.5,"cache_read":0.22,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":16.5,"cache_read":0.22,"cache_write":5.5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol (US)","type":"chat"},{"id":"eu.amazon.nova-lite-v1:0","name":"Nova Lite (EU)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.069,"output":0.276,"cache_read":0.01725,"cache_write":0.069},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite (EU)","type":"chat"},{"id":"global.anthropic.claude-opus-5-5","name":"Claude Opus 5.5 (Global)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (Global)","type":"chat"},{"id":"deepseek.r1-v1:0","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":1.35,"output":5.4},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1","type":"chat"},{"id":"openai.gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.07,"output":0.2},"canonical_model_id":"openai/gpt-oss-safeguard-20b","display_name":"GPT OSS Safeguard 20B","type":"chat"},{"id":"anthropic.claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"global.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (Global)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"eu.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (EU)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.374,"output":3.157,"cache_read":0.0935,"cache_write":0.374},"canonical_model_id":"amazon/nova-2-lite","display_name":"Nova 2 Lite (EU)","type":"chat"},{"id":"us.amazon.nova-pro-v1:0","name":"Nova Pro (US)","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8},"canonical_model_id":"amazon/nova-pro","display_name":"Nova Pro (US)","type":"chat"},{"id":"jp.anthropic.claude-opus-5-5","name":"Claude Opus 5.5 (JP)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (JP)","type":"chat"},{"id":"anthropic.claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"global.anthropic.claude-sonnet-5-5","name":"Claude Sonnet 5.5 (Global)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 (Global)","type":"chat"},{"id":"openai.gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"tiers":[{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat"},{"id":"us.meta.llama4-maverick-17b-instruct-v1:0","name":"Llama 4 Maverick 17B Instruct (US)","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":8192},"cost":{"input":0.24,"output":0.97},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct (US)","type":"chat"},{"id":"apac.amazon.nova-micro-v1:0","name":"Nova Micro (APAC)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.037,"output":0.148,"cache_read":0.00925,"cache_write":0.037},"canonical_model_id":"amazon/nova-micro","display_name":"Nova Micro (APAC)","type":"chat"},{"id":"eu.anthropic.claude-sonnet-4-20250514-v1:0","name":"Claude Sonnet 4 (EU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"eu.anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5 (EU)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"global.openai.gpt-6-sol","name":"GPT-6 Sol (Global)","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol (Global)","type":"chat"},{"id":"eu.anthropic.claude-haiku-5-5","name":"Claude Haiku 5.5 (EU)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"tiers":[{"input":0.55,"output":2.75,"cache_read":0.055,"cache_write":0.6875,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (EU)","type":"chat"},{"id":"qwen.qwen3-coder-30b-a3b-v1:0","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-31","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"us.amazon.nova-premier-v1:0","name":"Nova Premier (US)","description":"Multimodal model for complex analysis, long-context understanding, tool use, and model distillation","family":"nova","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-04-30","last_updated":"2025-04-30","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":10000},"status":"deprecated","cost":{"input":2.5,"output":12.5,"cache_read":0.625,"cache_write":2.5},"canonical_model_id":"amazon/nova-premier","display_name":"Nova Premier (US)","type":"chat"},{"id":"anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"meta.llama3-1-70b-instruct-v1:0","name":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.72,"output":0.72},"canonical_model_id":"meta/llama-3.1-70b-instruct","display_name":"Llama 3.1 70B Instruct","type":"chat"},{"id":"us.writer.palmyra-x4-v1:0","name":"Palmyra X4 (US)","description":"Enterprise language model for workflow automation, coding, data analysis, and tool use","family":"palmyra","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2024-10-09","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":122880,"output":8192},"cost":{"input":2.5,"output":10},"canonical_model_id":"writer/palmyra-x4","display_name":"Palmyra X4 (US)","type":"chat"},{"id":"us.zai.glm-5.3","name":"GLM-5.3 (US)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.848,"output":5.808,"cache_read":0.3432,"cache_write":2.31},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"apac.amazon.nova-pro-v1:0","name":"Nova Pro (APAC)","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.84,"output":3.36,"cache_read":0.21,"cache_write":0.84},"canonical_model_id":"amazon/nova-pro","display_name":"Nova Pro (APAC)","type":"chat"},{"id":"global.zai.glm-5.3","name":"GLM-5.3 (Global)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.68,"output":5.28,"cache_read":0.312,"cache_write":2.1},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"global.anthropic.claude-fable-5-1","name":"Claude Fable 5.1 (Global)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"us.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (US)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (US)","type":"chat"},{"id":"amazon.nova-micro-v1:0","name":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035},"canonical_model_id":"amazon/nova-micro","display_name":"Nova Micro","type":"chat"},{"id":"minimax.minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":98304},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"xai.grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-06-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat"},{"id":"us.amazon.nova-lite-v1:0","name":"Nova Lite (US)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite (US)","type":"chat"},{"id":"amazon.nova-pro-v1:0","name":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.8,"output":3.2,"cache_read":0.2,"cache_write":0.8},"canonical_model_id":"amazon/nova-pro","display_name":"Nova Pro","type":"chat"},{"id":"qwen.qwen3-32b-v1:0","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"openai.gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-06-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":5.5,"output":33,"cache_read":0.55},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat"},{"id":"jp.anthropic.claude-haiku-5-5","name":"Claude Haiku 5.5 (JP)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"tiers":[{"input":0.55,"output":2.75,"cache_read":0.055,"cache_write":0.6875,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (JP)","type":"chat"},{"id":"mistral.voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/voxtral-small-24b-2507","display_name":"Voxtral Small 24B 2507","type":"chat"},{"id":"global.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (Global)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.3},"canonical_model_id":"amazon/nova-2-lite","display_name":"Nova 2 Lite (Global)","type":"chat"},{"id":"us.openai.gpt-5.6-terra","name":"GPT-5.6 Terra (US)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra (US)","type":"chat"},{"id":"mistral.devstral-2-123b","name":"Devstral 2 123B","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2 123B","type":"chat"},{"id":"us.xai.grok-4.6","name":"Grok 4.6 (US)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2.2,"output":6.6,"cache_read":0.55},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6 (US)","type":"chat"},{"id":"jp.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (JP)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (JP)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic.claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"global.anthropic.claude-haiku-5-5","name":"Claude Haiku 5.5 (Global)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (Global)","type":"chat"},{"id":"anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"jp.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (JP)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (JP)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"us.openai.gpt-5.6-luna","name":"GPT-5.6 Luna (US)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"tiers":[{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna (US)","type":"chat"},{"id":"in.anthropic.claude-opus-5","name":"Claude Opus 5 (India)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (India)","type":"chat"},{"id":"us.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (US)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"au.anthropic.claude-opus-5","name":"Claude Opus 5 (AU)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (AU)","type":"chat"},{"id":"nvidia.nemotron-nano-12b-v2","name":"NVIDIA Nemotron Nano 12B v2 VL BF16","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.2,"output":0.6},"canonical_model_id":"nvidia/nemotron-nano-12b-v2-vl","display_name":"NVIDIA Nemotron Nano 12B v2 VL BF16","type":"chat"},{"id":"openai.gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"ultrafast":{"cost":{"input":13.2,"output":66,"cache_read":0.66,"cache_write":16.5},"provider":{"body":{"service_tier":"ultrafast"}}}}},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75,"tiers":[{"input":4.4,"output":16.5,"cache_read":0.22,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":16.5,"cache_read":0.22,"cache_write":5.5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"us.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (US)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.33,"output":2.75,"cache_read":0.0825,"cache_write":0.33},"canonical_model_id":"amazon/nova-2-lite","display_name":"Nova 2 Lite (US)","type":"chat"},{"id":"us.openai.gpt-6-astra","name":"GPT-6 Astra (US)","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"ultrafast":{"cost":{"input":66,"output":330,"cache_read":6.6,"cache_write":82.5},"provider":{"body":{"additionalModelRequestFields":{"service_tier":"ultrafast"}}}}}},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"tiers":[{"input":22,"output":82.5,"cache_read":2.2,"cache_write":27.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":22,"output":82.5,"cache_read":2.2,"cache_write":27.5}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra (US)","type":"chat"},{"id":"openai.gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat"},{"id":"global.openai.gpt-6.1-sol","name":"GPT-6.1 Sol (Global)","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"ultrafast":{"cost":{"input":12,"output":60,"cache_read":0.6,"cache_write":15},"provider":{"body":{"additionalModelRequestFields":{"service_tier":"ultrafast"}}}}}},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol (Global)","type":"chat"},{"id":"anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"us.anthropic.claude-opus-4-1-20250805-v1:0","name":"Claude Opus 4.1 (US)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"us.meta.llama3-1-8b-instruct-v1:0","name":"Llama 3.1 8B Instruct (US)","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.22,"output":0.22},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama 3.1 8B Instruct (US)","type":"chat"},{"id":"eu.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (EU)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"global.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (Global)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"apac.anthropic.claude-sonnet-4-20250514-v1:0","name":"Claude Sonnet 4 (APAC)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4 (APAC)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"deepseek.v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2026-02-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":81920},"cost":{"input":0.62,"output":1.85},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"qwen.qwen3-235b-a22b-2507-v1:0","name":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.22,"output":0.88},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507","type":"chat"},{"id":"amazon.nova-lite-v1:0","name":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.06,"output":0.24,"cache_read":0.015,"cache_write":0.06},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite","type":"chat"},{"id":"global.anthropic.claude-opus-5","name":"Claude Opus 5 (Global)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (Global)","type":"chat"},{"id":"openai.gpt-oss-20b-1:0","name":"gpt-oss-20b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":128000},"cost":{"input":0.07,"output":0.3},"canonical_model_id":"openai/gpt-oss-20b","display_name":"gpt-oss-20b","type":"chat"},{"id":"anthropic.claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat"},{"id":"anthropic.claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"meta.llama3-3-70b-instruct-v1:0","name":"Llama 3.3 70B Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.72,"output":0.72},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"minimax.minimax-m2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204608,"output":128000},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax-M2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"mistral.mistral-large-3-675b-instruct","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"in.openai.gpt-5.6-luna","name":"GPT-5.6 Luna (India)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"tiers":[{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna (India)","type":"chat"},{"id":"eu.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (EU)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"global.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (Global)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"zai.glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":2.2},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"au.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (AU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (AU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"eu.anthropic.claude-opus-5-5","name":"Claude Opus 5.5 (EU)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (EU)","type":"chat"},{"id":"global.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (Global)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"jp.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (JP)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (JP)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"google.gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.23,"output":0.38},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT","type":"chat"},{"id":"eu.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (EU)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"us.anthropic.claude-opus-5-5","name":"Claude Opus 5.5 (US)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (US)","type":"chat"},{"id":"us.anthropic.claude-opus-5","name":"Claude Opus 5 (US)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (US)","type":"chat"},{"id":"global.xai.grok-4.7","name":"Grok 4.7 (Global)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7 (Global)","type":"chat"},{"id":"us.openai.gpt-5.6-sol","name":"GPT-5.6 Sol (US)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5,"tiers":[{"input":8.8,"output":33,"cache_read":0.88,"cache_write":11,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8.8,"output":33,"cache_read":0.88,"cache_write":11}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol (US)","type":"chat"},{"id":"us.moonshotai.kimi-k3","name":"Kimi K3 (US)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"anthropic.claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat"},{"id":"mistral.magistral-small-2509","name":"Magistral Small 1.2","description":"Open multimodal reasoning model for transparent analysis of text and images","family":"magistral","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-18","last_updated":"2025-09-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":40000},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/magistral-small-2509","display_name":"Magistral Small 1.2","type":"chat"},{"id":"mistral.pixtral-large-2502-v1:0","name":"Pixtral Large (25.02)","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-04-08","last_updated":"2025-04-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2,"output":6},"canonical_model_id":"mistral/pixtral-large-2502","display_name":"Pixtral Large (25.02)","type":"chat"},{"id":"anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"nvidia.nemotron-nano-9b-v2","name":"NVIDIA Nemotron Nano 9B v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.06,"output":0.23},"canonical_model_id":"nvidia/nemotron-nano-9b-v2","display_name":"NVIDIA Nemotron Nano 9B v2","type":"chat"},{"id":"eu.amazon.nova-micro-v1:0","name":"Nova Micro (EU)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.04,"output":0.16,"cache_read":0.01,"cache_write":0.04},"canonical_model_id":"amazon/nova-micro","display_name":"Nova Micro (EU)","type":"chat"},{"id":"zai.glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"us.meta.llama3-1-70b-instruct-v1:0","name":"Llama 3.1 70B Instruct (US)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.72,"output":0.72},"canonical_model_id":"meta/llama-3.1-70b-instruct","display_name":"Llama 3.1 70B Instruct (US)","type":"chat"},{"id":"jp.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (JP)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (JP)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"nvidia.nemotron-nano-3-30b","name":"NVIDIA Nemotron Nano 3 30B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.06,"output":0.24},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"NVIDIA Nemotron Nano 3 30B","type":"chat"},{"id":"mistral.ministral-3-3b-instruct","name":"Ministral 3 3B","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.1,"output":0.1},"canonical_model_id":"mistral/ministral-3-3b-instruct-2512","display_name":"Ministral 3 3B","type":"chat"},{"id":"us.xai.grok-4.7","name":"Grok 4.7 (US)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2.2,"output":6.6,"cache_read":0.55},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7 (US)","type":"chat"},{"id":"us.openai.gpt-6-luna","name":"GPT-6 Luna (US)","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"tiers":[{"input":0.22,"output":0.825,"cache_read":0.022,"cache_write":0.275,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.22,"output":0.825,"cache_read":0.022,"cache_write":0.275}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna (US)","type":"chat"},{"id":"global.openai.gpt-5.6-sol","name":"GPT-5.6 Sol (Global)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol (Global)","type":"chat"},{"id":"google.gemma-4-26b-a4b","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":0.13,"output":0.4},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"xai.grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.2,"output":6.6,"cache_read":0.55},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat"},{"id":"global.xai.grok-4.6","name":"Grok 4.6 (Global)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6 (Global)","type":"chat"},{"id":"au.anthropic.claude-opus-4-6-v1","name":"AU Anthropic Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"AU Anthropic Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"qwen.qwen3-vl-235b-a22b","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262000},"cost":{"input":0.53,"output":2.66},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"anthropic.claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"jp.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (JP)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (JP)","type":"chat"},{"id":"us.anthropic.claude-sonnet-5-5","name":"Claude Sonnet 5.5 (US)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 (US)","type":"chat"},{"id":"qwen.qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.5,"output":1.2},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"anthropic.claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"au.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (AU)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (AU)","type":"chat"},{"id":"meta.llama4-scout-17b-instruct-v1:0","name":"Llama 4 Scout 17B Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":10000000,"output":8192},"cost":{"input":0.17,"output":0.66},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B Instruct","type":"chat"},{"id":"openai.gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-safeguard-120b","display_name":"GPT OSS Safeguard 120B","type":"chat"},{"id":"us.meta.llama3-3-70b-instruct-v1:0","name":"Llama 3.3 70B Instruct (US)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.72,"output":0.72},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct (US)","type":"chat"},{"id":"global.openai.gpt-5.6-luna","name":"GPT-5.6 Luna (Global)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna (Global)","type":"chat"},{"id":"au.anthropic.claude-sonnet-4-6","name":"AU Anthropic Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"AU Anthropic Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"openai.gpt-oss-120b","name":"gpt-oss-120b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/v1","shape":"responses"},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"gpt-oss-120b","type":"chat"},{"id":"deepseek.v3-v1:0","name":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":81920},"cost":{"input":0.58,"output":1.68},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek-V3.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"moonshotai.kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.6,"output":3},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"eu.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (EU)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"us-gov.openai.gpt-oss-120b-1:0","name":"gpt-oss-120b (GovCloud)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.18,"output":0.72},"canonical_model_id":"openai/gpt-oss-120b","display_name":"gpt-oss-120b (GovCloud)","type":"chat"},{"id":"us.anthropic.claude-fable-5","name":"Claude Fable 5 (US)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"openai.gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":16.5,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":16.5,"cache_read":0.44,"cache_write":5.5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"us.deepseek.r1-v1:0","name":"DeepSeek-R1 (US)","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":1.35,"output":5.4},"canonical_model_id":"deepseek/deepseek-r1","display_name":"DeepSeek-R1 (US)","type":"chat"},{"id":"eu.anthropic.claude-opus-5","name":"Claude Opus 5 (EU)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (EU)","type":"chat"},{"id":"ca.amazon.nova-lite-v1:0","name":"Nova Lite (CA)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.064,"output":0.256,"cache_read":0.016,"cache_write":0.064},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite (CA)","type":"chat"},{"id":"us.openai.gpt-6-sol","name":"GPT-6 Sol (US)","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":16.5,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":16.5,"cache_read":0.44,"cache_write":5.5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol (US)","type":"chat"},{"id":"au.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (AU)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (AU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"us.meta.llama4-scout-17b-instruct-v1:0","name":"Llama 4 Scout 17B Instruct (US)","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":10000000,"output":8192},"cost":{"input":0.17,"output":0.66},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B Instruct (US)","type":"chat"},{"id":"global.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (Global)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (Global)","type":"chat"},{"id":"global.anthropic.claude-fable-5","name":"Claude Fable 5 (Global)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"apac.amazon.nova-lite-v1:0","name":"Nova Lite (APAC)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.063,"output":0.252,"cache_read":0.01575,"cache_write":0.063},"canonical_model_id":"amazon/nova-lite","display_name":"Nova Lite (APAC)","type":"chat"},{"id":"in.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (India)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (India)","type":"chat"},{"id":"us.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (US)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"nvidia.nemotron-super-3-120b","name":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.65},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"NVIDIA Nemotron 3 Super 120B A12B","type":"chat"},{"id":"global.openai.gpt-6-luna","name":"GPT-6 Luna (Global)","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna (Global)","type":"chat"},{"id":"us-gov.openai.gpt-oss-20b-1:0","name":"gpt-oss-20b (GovCloud)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.084,"output":0.36},"canonical_model_id":"openai/gpt-oss-20b","display_name":"gpt-oss-20b (GovCloud)","type":"chat"},{"id":"us.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (US)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"meta.llama3-1-8b-instruct-v1:0","name":"Llama 3.1 8B Instruct","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.22,"output":0.22},"canonical_model_id":"meta/llama-3.1-8b-instruct","display_name":"Llama 3.1 8B Instruct","type":"chat"},{"id":"writer.palmyra-x5-v1:0","name":"Palmyra X5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"palmyra","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1040000,"input":1040000,"output":8192},"cost":{"input":0.6,"output":6},"canonical_model_id":"writer/palmyra-x5","display_name":"Palmyra X5","type":"chat"},{"id":"anthropic.claude-opus-4-1-20250805-v1:0","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"us.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (US)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"global.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (Global)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"eu.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (EU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"jp.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (JP)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (JP)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"us.anthropic.claude-haiku-5-5","name":"Claude Haiku 5.5 (US)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"tiers":[{"input":0.55,"output":2.75,"cache_read":0.055,"cache_write":0.6875,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (US)","type":"chat"},{"id":"au.anthropic.claude-opus-5-5","name":"Claude Opus 5.5 (AU)","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.4,"output":22,"cache_read":0.22,"cache_write":5.5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5 (AU)","type":"chat"},{"id":"openai.gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"tiers":[{"input":0.22,"output":0.825,"cache_read":0.022,"cache_write":0.275,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.22,"output":0.825,"cache_read":0.022,"cache_write":0.275}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"writer.palmyra-x4-v1:0","name":"Palmyra X4","description":"Enterprise language model for workflow automation, coding, data analysis, and tool use","family":"palmyra","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2024-10-09","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":122880,"output":8192},"cost":{"input":2.5,"output":10},"canonical_model_id":"writer/palmyra-x4","display_name":"Palmyra X4","type":"chat"},{"id":"global.anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5 (Global)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic.claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"us.anthropic.claude-sonnet-4-20250514-v1:0","name":"Claude Sonnet 4 (US)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"eu.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (EU)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5 (EU)","type":"chat"},{"id":"zai.glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.07,"output":0.4},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"moonshot.kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16000},"cost":{"input":0.6,"output":2.5},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"eu.amazon.nova-pro-v1:0","name":"Nova Pro (EU)","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.92,"output":3.68,"cache_read":0.23,"cache_write":0.92},"canonical_model_id":"amazon/nova-pro","display_name":"Nova Pro (EU)","type":"chat"},{"id":"global.openai.gpt-5.6-terra","name":"GPT-5.6 Terra (Global)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra (Global)","type":"chat"},{"id":"openai.gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"ultrafast":{"cost":{"input":66,"output":330,"cache_read":6.6,"cache_write":82.5},"provider":{"body":{"service_tier":"ultrafast"}}}}},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75,"tiers":[{"input":22,"output":82.5,"cache_read":2.2,"cache_write":27.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":22,"output":82.5,"cache_read":2.2,"cache_write":27.5}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat"},{"id":"us.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (US)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"meta.llama4-maverick-17b-instruct-v1:0","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":8192},"cost":{"input":0.24,"output":0.97},"canonical_model_id":"meta/llama-4-maverick-17b-instruct","display_name":"Llama 4 Maverick 17B Instruct","type":"chat"},{"id":"qwen.qwen3-next-80b-a3b","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-11","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262000},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct","type":"chat"},{"id":"eu.mistral.pixtral-large-2502-v1:0","name":"Pixtral Large (25.02) (EU)","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-04-08","last_updated":"2025-04-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2,"output":6},"canonical_model_id":"mistral/pixtral-large-2502","display_name":"Pixtral Large (25.02) (EU)","type":"chat"},{"id":"au.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (AU)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (AU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"au.anthropic.claude-haiku-5-5","name":"Claude Haiku 5.5 (AU)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.11,"output":0.55,"cache_read":0.011,"cache_write":0.1375,"tiers":[{"input":0.55,"output":2.75,"cache_read":0.055,"cache_write":0.6875,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5 (AU)","type":"chat"},{"id":"us.anthropic.claude-fable-5-1","name":"Claude Fable 5.1 (US)","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":0.275,"cache_write":13.75},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"global.moonshotai.kimi-k3","name":"Kimi K3 (Global)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"in.openai.gpt-5.6-terra","name":"GPT-5.6 Terra (India)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra (India)","type":"chat"},{"id":"openai.gpt-oss-20b","name":"gpt-oss-20b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/v1","shape":"responses"},"cost":{"input":0.07,"output":0.3},"canonical_model_id":"openai/gpt-oss-20b","display_name":"gpt-oss-20b","type":"chat"},{"id":"mistral.ministral-3-14b-instruct","name":"Ministral 14B 3.0","description":"Open vision-language model for efficient local deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.2,"output":0.2},"canonical_model_id":"mistral/ministral-3-14b-instruct-2512","display_name":"Ministral 14B 3.0","type":"chat"},{"id":"au.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (AU)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (AU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"openai.gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":4.4,"output":22,"cache_read":0.44,"cache_write":5.5,"tiers":[{"input":8.8,"output":33,"cache_read":0.88,"cache_write":11,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8.8,"output":33,"cache_read":0.88,"cache_write":11}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat"},{"id":"minimax.minimax-m2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.3,"output":1.2},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"us.anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5 (US)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5 (US)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"eu.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (EU)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7 (EU)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"jp.amazon.nova-2-lite-v1:0","name":"Nova 2 Lite (JP)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.396,"output":3.311,"cache_read":0.099,"cache_write":0.396},"canonical_model_id":"amazon/nova-2-lite","display_name":"Nova 2 Lite (JP)","type":"chat"},{"id":"us.mistral.pixtral-large-2502-v1:0","name":"Pixtral Large (25.02) (US)","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-04-08","last_updated":"2025-04-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2,"output":6},"canonical_model_id":"mistral/pixtral-large-2502","display_name":"Pixtral Large (25.02) (US)","type":"chat"},{"id":"jp.anthropic.claude-opus-5","name":"Claude Opus 5 (JP)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5 (JP)","type":"chat"},{"id":"global.anthropic.claude-sonnet-4-20250514-v1:0","name":"Claude Sonnet 4 (Global)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"global.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (Global)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8 (Global)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"openai.gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-06-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.75,"output":16.5,"cache_read":0.275},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat"},{"id":"mistral.voxtral-mini-3b-2507","name":"Voxtral Mini 3B 2507","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","family":"voxtral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":4096},"cost":{"input":0.04,"output":0.04},"canonical_model_id":"mistral/voxtral-mini-3b-2507","display_name":"Voxtral Mini 3B 2507","type":"chat"},{"id":"openai.gpt-oss-120b-1:0","name":"gpt-oss-120b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":128000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-oss-120b","display_name":"gpt-oss-120b","type":"chat"},{"id":"amazon.nova-2-lite-v1:0","name":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.33,"output":2.75,"cache_read":0.0825,"cache_write":0.33},"canonical_model_id":"amazon/nova-2-lite","display_name":"Nova 2 Lite","type":"chat"},{"id":"eu.anthropic.claude-sonnet-5-5","name":"Claude Sonnet 5.5 (EU)","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5 (EU)","type":"chat"},{"id":"us.amazon.nova-micro-v1:0","name":"Nova Micro (US)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":0.035},"canonical_model_id":"amazon/nova-micro","display_name":"Nova Micro (US)","type":"chat"},{"id":"mistral.ministral-3-8b-instruct","name":"Ministral 3 8B","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.15,"output":0.15},"canonical_model_id":"mistral/ministral-3-8b-instruct-2512","display_name":"Ministral 3 8B","type":"chat"},{"id":"in.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (India)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5 (India)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}}]},"synthetic":{"id":"synthetic","api":"https://api.synthetic.new/openai/v1","name":"Synthetic","doc":"https://synthetic.new/pricing","display_name":"Synthetic","models":[{"id":"hf:moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":3,"output":15,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hf:moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.95},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":1,"cache_read":0.3},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"hf:zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hf:zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":0.15,"output":0.5,"cache_read":0.04},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hf:zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":65536},"cost":{"input":0.1,"output":0.5,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hf:zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"hf:deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":0.6,"output":1.2,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"hf:Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":3.6,"cache_read":0.45},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"hf:openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"hf:MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":0.6,"output":1.2,"cache_read":0.6},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"llmgateway":{"id":"llmgateway","api":"https://api.llmgateway.io/v1","name":"DevPass (LLM Gateway)","doc":"https://llmgateway.io/docs","display_name":"DevPass (LLM Gateway)","models":[{"id":"grok-4-1-fast-reasoning","name":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"canonical_model_id":"zhipuai/glm-4.6v","display_name":"GLM-4.6V","type":"chat"},{"id":"qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0.0625},"canonical_model_id":"alibaba/qwen-flash","display_name":"Qwen Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5","display_name":"GLM-4.5","type":"chat"},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.25,"cache_read":0.01},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"reka-edge-2603","name":"Reka Edge 2603","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-09","last_updated":"2026-10-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"cost":{"input":0.1,"output":0.1},"display_name":"Reka Edge 2603","type":"chat"},{"id":"grok-4-5","name":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"display_name":"Grok 4.5","type":"chat"},{"id":"gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5,"cache_read":0},"canonical_model_id":"openai/gpt-3.5-turbo","display_name":"GPT-3.5-turbo","type":"chat"},{"id":"grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"display_name":"Grok 4.1 Fast Non-Reasoning","type":"chat"},{"id":"qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.07,"output":0.3,"cache_read":0.015},"display_name":"Seed 1.6 Flash (250715)","type":"chat"},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.3","name":"Muse Spark 1.3","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.3","display_name":"Muse Spark 1.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen3.8-27B","name":"Qwen3.8 27B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":32768},"cost":{"input":0.08,"output":0.35,"cache_read":0.05},"display_name":"Qwen3.8 27B","type":"chat"},{"id":"gpt-4o-transcribe","name":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":2.5,"output":10},"display_name":"GPT-4o Transcribe","type":"chat"},{"id":"mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.168,"output":0.336,"cache_read":0.0034,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":262144},"cost":{"input":4,"output":12},"canonical_model_id":"mistral/mistral-large-latest","display_name":"Mistral Large (latest)","type":"chat"},{"id":"seed-2-0-code-preview-260328","name":"Seed 2.0 Code Preview (260328)","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":3,"cache_read":0.1},"display_name":"Seed 2.0 Code Preview (260328)","type":"chat"},{"id":"qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.98,"output":3.95},"display_name":"Qwen3 VL 235B A22B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1010000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2-codex","display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1-codex","display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5v-turbo","display_name":"GLM-5V-Turbo","type":"chat"},{"id":"gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":1.6,"reasoning":4.8,"cache_read":0.04,"cache_write":0.25},"canonical_model_id":"alibaba/qwen3-vl-plus","display_name":"Qwen3-VL Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.088,"output":0.25,"cache_read":0.025},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"fugu-max","name":"Fugu Max","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2,"output":6,"cache_read":0.25},"display_name":"Fugu Max","type":"chat"},{"id":"ministral-8b-2512","name":"Ministral 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.15},"display_name":"Ministral 8B","type":"chat"},{"id":"qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"canonical_model_id":"alibaba/qwen3.5-27b","display_name":"Qwen3.5 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2,"cache_read":0.11,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.6","display_name":"GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2-fast","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2.156,"output":6.776,"cache_read":0.429},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat"},{"id":"muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.04},"canonical_model_id":"meta/muse-glimmer-30b","display_name":"Muse Glimmer 30B","type":"chat"},{"id":"grok-build-0-1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat"},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct (2507)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.09,"output":0.58},"display_name":"Qwen3 235B A22B Instruct (2507)","type":"chat"},{"id":"qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4},"canonical_model_id":"alibaba/qwen-max","display_name":"Qwen Max","type":"chat"},{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-thinking","display_name":"Qwen3-Next 80B-A3B (Thinking)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.54,"output":4.631,"cache_read":0.198,"cache_write":2.5},"canonical_model_id":"alibaba/qwen3.8-max-preview","display_name":"Qwen3.8 Max Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.108,"output":0.675,"cache_read":0.06},"display_name":"Qwen3 Coder Next","type":"chat"},{"id":"glm-4.5-x","name":"GLM-4.5 X","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"beta","cost":{"input":2.2,"output":8.9,"cache_read":0.45},"display_name":"GLM-4.5 X","type":"chat"},{"id":"grok-4","name":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":3,"output":15,"cache_read":0.75},"display_name":"Grok 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":262144},"cost":{"input":1.36,"output":4.18,"cache_read":0.14},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":2048},"cost":{"input":0.27,"output":0.85},"display_name":"Llama 4 Maverick 17B Instruct","type":"chat"},{"id":"gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"canonical_model_id":"openai/gpt-5.2-pro","display_name":"GPT-5.2 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"canonical_model_id":"openai/o4-mini","display_name":"o4-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"canonical_model_id":"openai/o3-mini","display_name":"o3-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131072},"cost":{"input":0.72,"output":2.3,"cache_read":0.144,"cache_write":0},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"fugu-ultra-v2.0","name":"Fugu Ultra v2.0","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5},"display_name":"Fugu Ultra v2.0","type":"chat"},{"id":"gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"canonical_model_id":"openai/gpt-4","display_name":"GPT-4","type":"chat"},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":384000},"cost":{"input":0.135,"output":0.54,"cache_read":0.0027},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":228700,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3-fast","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1040384,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat"},{"id":"qwen3-32b","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.36,"output":0.87,"reasoning":8.4},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.1","display_name":"Muse Spark 1.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":1.2,"reasoning":4,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen-plus","display_name":"Qwen Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.7-flash","name":"Qwen3.7 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-27","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":1000000},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.0375},"display_name":"Qwen3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3.05,"cache_read":0.13},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"minimax-m2.1-lightning","name":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.12,"output":0.48},"display_name":"MiniMax M2.1 Lightning","type":"chat"},{"id":"claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.845,"output":3.38,"cache_read":0.6,"cache_write":3.75},"canonical_model_id":"alibaba/qwen3-max","display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"glm-4.5-airx","name":"GLM-4.5 AirX","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":4.5,"cache_read":0.22},"display_name":"GLM-4.5 AirX","type":"chat"},{"id":"glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"canonical_model_id":"zhipuai/glm-4.5v","display_name":"GLM-4.5V","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":2048},"cost":{"input":0.18,"output":0.59},"display_name":"Llama 4 Scout 17B Instruct","type":"chat"},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":8192},"cost":{"input":0.2,"output":0.8},"display_name":"Qwen3 235B A22B FP8","type":"chat"},{"id":"o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"canonical_model_id":"openai/o1","display_name":"o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-4-32b-0414-128k","name":"GLM-4 32B (0414-128k)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.1,"output":0.1},"display_name":"GLM-4 32B (0414-128k)","type":"chat"},{"id":"qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.38,"output":1.55},"canonical_model_id":"alibaba/qwen3-coder-480b-a35b-instruct","display_name":"Qwen3-Coder 480B-A35B Instruct","type":"chat"},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":0.07,"output":0.27},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"mistral-medium-3-5","name":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"display_name":"Mistral Medium 3.5","type":"chat"},{"id":"ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"display_name":"InclusionAI Ling 3.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.06},"canonical_model_id":"moonshotai/kimi-k2-thinking","display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-4-1-20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"canonical_model_id":"openai/gpt-5-pro","display_name":"GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.6},"display_name":"Qwen3 VL 30B A3B Instruct","type":"chat"},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"seed-1-6-250915","name":"Seed 1.6 (250915)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 1.6 (250915)","type":"chat"},{"id":"ling-3.1-flash","name":"Ling 3.1 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"inclusionai/ling-3.1-flash","display_name":"Ling 3.1 Flash","type":"chat"},{"id":"seed-2-0-mini-260428","name":"Seed 2.0 Mini (260428)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.4,"cache_read":0.02},"display_name":"Seed 2.0 Mini (260428)","type":"chat"},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.07,"output":0.34},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-3-70b-instruct","name":"Llama 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-04-18","last_updated":"2024-04-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8000},"cost":{"input":0.51,"output":0.74},"display_name":"Llama 3 70B Instruct","type":"chat"},{"id":"seed-2-0-pro-260328","name":"Seed 2.0 Pro (260328)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":3,"cache_read":0.1},"display_name":"Seed 2.0 Pro (260328)","type":"chat"},{"id":"ling-3.0-flash-vl","name":"Ling 3.0 Flash VL","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"display_name":"Ling 3.0 Flash VL","type":"chat"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking (2507)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":8192},"cost":{"input":0.3,"output":3},"display_name":"Qwen3 235B A22B Thinking (2507)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-03","last_updated":"2026-09-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":1050000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-text-01","name":"MiniMax Text 01","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.2,"output":1.1},"display_name":"MiniMax Text 01","type":"chat"},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-4.6v-flashx","name":"GLM-4.6V FlashX","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.04,"output":0.4,"cache_read":0.004},"display_name":"GLM-4.6V FlashX","type":"chat"},{"id":"qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-4-20-beta-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.405,"output":1.98,"cache_read":0.225},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.135,"output":0.4},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"canonical_model_id":"alibaba/qwen3-next-80b-a3b-instruct","display_name":"Qwen3-Next 80B-A3B Instruct","type":"chat"},{"id":"granite-4.2-8b","name":"Granite 4.2 8B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"granite","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.06,"output":0.25,"cache_read":0.015},"display_name":"Granite 4.2 8B","type":"chat"},{"id":"fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-22","last_updated":"2026-06-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5},"display_name":"Fugu Ultra","type":"chat"},{"id":"gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32766},"cost":{"input":0.04,"output":0.19,"cache_read":0.01},"display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.08,"output":0.32,"cache_read":0.017,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.05,"cache_write":0.3125},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":997952,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"alibaba/qwen3-coder-flash","display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"nemotron-3-ultra-550b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.5,"output":2.2,"cache_read":0.1},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat"},{"id":"llama-3.2-11b-instruct","name":"Llama 3.2 11B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.07,"output":0.33},"display_name":"Llama 3.2 11B Instruct","type":"chat"},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.06,"output":0.4,"cache_read":0.01,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.15},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-1.2","display_name":"Muse Spark 1.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.12,"output":0.25,"cache_read":0.0025},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"seed-1-8-251228","name":"Seed 1.8 (251228)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 1.8 (251228)","type":"chat"},{"id":"glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.38,"output":1.98,"cache_read":0.19,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.28,"output":1.1,"cache_read":0.05},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"seed-1-6-250615","name":"Seed 1.6 (250615)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 1.6 (250615)","type":"chat"},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"qwen35-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat"},{"id":"gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"canonical_model_id":"alibaba/qwen3.5-35b-a3b","display_name":"Qwen3.5 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.605,"output":2.123,"cache_read":0.154,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":123000,"output":123000},"cost":{"input":0.42,"output":1.25},"display_name":"ERNIE 4.5 VL 424B A47B","type":"chat"},{"id":"hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":128000},"cost":{"input":0.132,"output":0.528,"cache_read":0.033},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"seed-2-0-lite-260428","name":"Seed 2.0 Lite (260428)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":2,"cache_read":0.05},"display_name":"Seed 2.0 Lite (260428)","type":"chat"},{"id":"kimi-k2","name":"Kimi K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.57,"output":2.3,"cache_read":0.5},"display_name":"Kimi K2","type":"chat"},{"id":"hy-mt2-plus","name":"Hy-MT2 Plus","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"Hy","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.074,"output":0.295},"display_name":"Hy-MT2 Plus","type":"chat"},{"id":"grok-4-3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat"},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.931,"output":2.93,"cache_read":0.173,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"grok-4-20-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"grok-4-20-beta-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.7-highspeed","display_name":"MiniMax-M2.7-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.7-flashx","display_name":"GLM-4.7-FlashX","type":"chat"},{"id":"muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.2 Contributor","type":"chat"},{"id":"sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":130000,"output":4096},"cost":{"input":0.25,"output":2.5,"cache_write":0.25},"canonical_model_id":"perplexity/sonar","display_name":"Sonar","type":"chat"},{"id":"mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"grok-4-6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat"},{"id":"gemini-pro-latest","name":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-27","last_updated":"2026-02-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"display_name":"Gemini Pro Latest","type":"chat"},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"minimax-m2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375},"canonical_model_id":"minimax/MiniMax-M2.5-highspeed","display_name":"MiniMax-M2.5-highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"ministral-14b-2512","name":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.2,"output":0.2},"display_name":"Ministral 14B","type":"chat"},{"id":"glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"canonical_model_id":"stepfun/step-3.7-flash","display_name":"Step 3.7 Flash","type":"chat"},{"id":"muse-wonder-1.0","name":"Muse Wonder","description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-12","last_updated":"2026-10-12","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"meta/muse-wonder-1.0","display_name":"Muse Wonder","type":"chat"},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":1.25,"output":5},"display_name":"GPT-4o Mini Transcribe","type":"chat"},{"id":"llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"cost":{"input":0.03,"output":0.05},"display_name":"Llama 3.2 3B Instruct","type":"chat"},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistral-small-2506","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/mistral-small-2506","display_name":"Mistral Small 3.2","type":"chat"},{"id":"grok-4-20-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4-7","name":"Grok 4.7","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"display_name":"Grok 4.7","type":"chat"},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":16384},"cost":{"input":0.26,"output":0.38,"cache_read":0.13},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"canonical_model_id":"openai/gpt-4-turbo","display_name":"GPT-4 Turbo","type":"chat"},{"id":"hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.3-contributor","name":"Muse Spark 1.3 Contributor","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"display_name":"Muse Spark 1.3 Contributor","type":"chat"},{"id":"glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":98304},"cost":{"input":0.13,"output":0.85,"cache_read":0.025,"cache_write":0},"canonical_model_id":"zhipuai/glm-4.5-air","display_name":"GLM-4.5-Air","type":"chat"},{"id":"qwen-plus-latest","name":"Qwen Plus Latest","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-01-25","last_updated":"2025-01-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":8192},"cost":{"input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5},"display_name":"Qwen Plus Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32766},"cost":{"input":0.032,"output":0.14,"cache_read":0.032},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5.1-codex-mini","display_name":"GPT-5.1 Codex mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"ministral-3b-2512","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.1,"output":0.1},"display_name":"Ministral 3B","type":"chat"},{"id":"o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"canonical_model_id":"openai/o3","display_name":"o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.5,"output":2,"cache_read":0.15},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.737,"output":3.08,"cache_read":0.143},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5.3-fast","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2.8,"output":8.8,"cache_read":0.56},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat"},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.27,"output":1.1},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":1050000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"auto","name":"Auto Route","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":{"supported":true},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"display_name":"Auto Route","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-3.1-70b-instruct","name":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":2048},"status":"beta","cost":{"input":0.72,"output":0.72},"display_name":"Llama 3.1 70B Instruct","type":"chat"},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Gemini multimodal model for text, image, audio, video, and document tasks","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-09-30","last_updated":"2026-09-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":0.375},"display_name":"Gemini 4 Argon","type":"chat"},{"id":"minimax-m2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.2,"output":1,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax-M2","type":"chat"},{"id":"custom","name":"Custom Model","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"display_name":"Custom Model","type":"chat"},{"id":"codestral-2508","name":"Codestral","description":"Mistral coding model for code completion, generation, and developer workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.3,"output":0.9},"display_name":"Codestral","type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":384000},"cost":{"input":0.076,"output":0.153,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"sap-ai-core":{"id":"sap-ai-core","name":"SAP AI Core","doc":"https://help.sap.com/docs/sap-ai-core","display_name":"SAP AI Core","models":[{"id":"anthropic--claude-4-opus","name":"anthropic--claude-4-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-20250514","display_name":"anthropic--claude-4-opus","type":"chat"},{"id":"gpt-5.4","name":"gpt-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"gpt-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"nvidia--llama-3.2-nv-embedqa-1b","name":"nvidia--llama-3.2-nv-embedqa-1b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.07,"output":0},"display_name":"nvidia--llama-3.2-nv-embedqa-1b","type":"chat"},{"id":"text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":1536},"cost":{"input":0.02,"output":0},"display_name":"text-embedding-3-small","type":"embedding"},{"id":"sap-abap-1","name":"sap-abap-1","description":"SAP-hosted model for ABAP code generation and enterprise development tasks","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-11-26","last_updated":"2025-11-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.48,"output":1.7},"display_name":"sap-abap-1","type":"chat"},{"id":"anthropic--claude-4.8-opus","name":"anthropic--claude-4.8-opus","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"anthropic--claude-4.8-opus","type":"chat"},{"id":"gpt-5-mini","name":"gpt-5-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"canonical_model_id":"openai/gpt-5-mini","display_name":"gpt-5-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"anthropic--claude-3-haiku","name":"anthropic--claude-3-haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"canonical_model_id":"anthropic/claude-3-haiku-20240307","display_name":"anthropic--claude-3-haiku","type":"chat"},{"id":"gpt-4.1-nano","name":"gpt-4.1-nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.08,"output":0.26},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"gpt-4.1-nano","type":"chat"},{"id":"gpt-5-nano","name":"gpt-5-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"canonical_model_id":"openai/gpt-5-nano","display_name":"gpt-5-nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"nvidia--llama-nemotron-embed-1b","type":"embedding","name":"Llama Nemotron Embed 1B v2","description":"Multilingual text embedding model for retrieval and question answering pipelines","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"canonical_model_id":"nvidia/llama-nemotron-embed-1b-v2","display_name":"Llama Nemotron Embed 1B v2"},{"id":"anthropic--claude-4.5-haiku","name":"anthropic--claude-4.5-haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"anthropic--claude-4.5-haiku","type":"chat"},{"id":"anthropic--claude-4.7-opus","name":"anthropic--claude-4.7-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"anthropic--claude-4.7-opus","type":"chat"},{"id":"gemini-embedding","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":1},"canonical_model_id":"google/gemini-embedding-001","display_name":"Gemini Embedding 001","type":"chat"},{"id":"gemini-embedding-2","name":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","family":"gemini","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":3072},"canonical_model_id":"google/gemini-embedding-2","display_name":"Gemini Embedding 2","type":"embedding"},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"amazon--nova-pro","name":"amazon--nova-pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":8192},"cost":{"input":0.56,"output":2.13},"display_name":"amazon--nova-pro","type":"chat"},{"id":"amazon--nova-lite","name":"amazon--nova-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.3,"output":2.37},"display_name":"amazon--nova-lite","type":"chat"},{"id":"sonar-pro","name":"sonar-pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"canonical_model_id":"perplexity/sonar-pro","display_name":"sonar-pro","type":"chat"},{"id":"anthropic--claude-3.5-sonnet","name":"anthropic--claude-3.5-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04-30","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-3-5-sonnet-20241022","display_name":"anthropic--claude-3.5-sonnet","type":"chat"},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.09,"output":0},"display_name":"text-embedding-3-large","type":"embedding"},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"amazon--nova-micro","name":"amazon--nova-micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.03,"output":0.1},"display_name":"amazon--nova-micro","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic--claude-4.5-opus","name":"anthropic--claude-4.5-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"anthropic--claude-4.5-opus","type":"chat"},{"id":"anthropic--claude-4-sonnet","name":"anthropic--claude-4-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"anthropic--claude-4-sonnet","type":"chat"},{"id":"gemini-3.5-flash","name":"gemini-3.5-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"gemini-3.5-flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro","name":"gemini-2.5-pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-25","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"google/gemini-2.5-pro","display_name":"gemini-2.5-pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"anthropic--claude-3-sonnet","name":"anthropic--claude-3-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-03-04","last_updated":"2024-03-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"anthropic--claude-3-sonnet","type":"chat"},{"id":"sonar-deep-research","name":"sonar-deep-research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"display_name":"sonar-deep-research","type":"chat"},{"id":"mistralai--mistral-small","name":"mistralai--mistral-small","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.07,"output":0.28},"canonical_model_id":"mistral/mistral-small-2603","display_name":"mistralai--mistral-small","type":"chat"},{"id":"gemini-2.5-flash","name":"gemini-2.5-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-17","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"canonical_model_id":"google/gemini-2.5-flash","display_name":"gemini-2.5-flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"anthropic--claude-3.7-sonnet","name":"anthropic--claude-3.7-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-24","last_updated":"2025-02-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-3-7-sonnet-20250219","display_name":"anthropic--claude-3.7-sonnet","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"gpt-5.6-luna","name":"gpt-5.6-luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"tiers":[{"input":2,"output":9,"cache_read":0.2,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"gpt-5.6-luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2","name":"gpt-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":9.44,"cache_read":0.12},"canonical_model_id":"openai/gpt-5.2","display_name":"gpt-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.5","name":"gpt-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"gpt-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"anthropic--claude-4.6-opus","name":"anthropic--claude-4.6-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"anthropic--claude-4.6-opus","type":"chat"},{"id":"mistralai--mistral-medium-instruct","name":"mistralai--mistral-medium-instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.36,"output":1.22},"canonical_model_id":"mistral/mistral-medium-2505","display_name":"mistralai--mistral-medium-instruct","type":"chat"},{"id":"gpt-4.1","name":"gpt-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.32},"canonical_model_id":"openai/gpt-4.1","display_name":"gpt-4.1","type":"chat"},{"id":"anthropic--claude-3-opus","name":"anthropic--claude-3-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-02-29","last_updated":"2024-02-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"anthropic--claude-3-opus","type":"chat"},{"id":"anthropic--claude-4.6-sonnet","name":"anthropic--claude-4.6-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"anthropic--claude-4.6-sonnet","type":"chat"},{"id":"sonar","name":"sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":1,"output":1},"canonical_model_id":"perplexity/sonar","display_name":"sonar","type":"chat"},{"id":"amazon--titan-embed-text","name":"amazon--titan-embed-text","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-04-30","last_updated":"2024-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.14,"output":0},"display_name":"amazon--titan-embed-text","type":"chat"},{"id":"gpt-4.1-mini","name":"gpt-4.1-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"gpt-4.1-mini","type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"gemini-2.5-flash-lite","name":"gemini-2.5-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"gemini-2.5-flash-lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5.6-terra","name":"gpt-5.6-terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"gpt-5.6-terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mistralai--mistral-medium","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"gpt-5","name":"gpt-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"gpt-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"anthropic--claude-4.5-sonnet","name":"anthropic--claude-4.5-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"anthropic--claude-4.5-sonnet","type":"chat"},{"id":"gpt-5.6-sol","name":"gpt-5.6-sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"gpt-5.6-sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"cohere--command-a-reasoning","name":"cohere--command-a-reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","family":"command-a","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]},{"type":"budget_tokens","min":1}],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.63,"output":5.05},"canonical_model_id":"cohere/command-a-reasoning-08-2025","display_name":"cohere--command-a-reasoning","type":"chat"},{"id":"gemini-3.1-flash-lite","name":"gemini-3.1-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"gemini-3.1-flash-lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"vivgrid":{"id":"vivgrid","api":"https://api.vivgrid.com/v1","name":"Vivgrid","doc":"https://docs.vivgrid.com/models","display_name":"Vivgrid","models":[{"id":"viv-fast","name":"Viv Fast","description":"Fast coding model","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-09","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":256000},"cost":{"input":0.13,"output":0.4,"cache_read":0.05},"canonical_model_id":"vivgrid/viv-fast","display_name":"Viv Fast","type":"chat"},{"id":"gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":2.5,"output":15,"cache_read":0.25},"display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.04},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"kimi-k3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.25,"output":2,"cache_read":0.03},"display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.31,"output":1.23,"cache_read":0.01},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":10,"output":50,"cache_read":0.5,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":10,"output":50,"cache_read":1.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.35,"output":3,"reasoning":3,"cache_read":0.05},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT 5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1 Codex Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.2,"output":4.2,"cache_read":0.3},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.75,"output":3.75,"cache_read":0.15},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"gpt-5.6-terra","name":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT 5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.28,"output":0.42},"display_name":"DeepSeek-V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.2,"output":4.2,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1},"display_name":"Gemini 3.1 Flash Lite Preview","type":"chat"},{"id":"gpt-5.6-sol","name":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT 5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.3,"reasoning":0.3,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"prime":{"id":"prime","api":"https://api.pinference.ai/api/v1","name":"Prime Inference","doc":"https://docs.primeintellect.ai/inference/overview","display_name":"Prime Inference","models":[{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":0.44,"output":1.32},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.3},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro 0423","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.91,"output":3.83},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro 0423","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash 0423","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943717},"cost":{"input":0.44,"output":1.32},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash 0423","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":1.04,"output":2.253},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"z-ai/glm-5.3-flash","name":"GLM 5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0.15},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM 5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":1.54,"output":4.84},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM 5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":1.4},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM 5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":1.25,"output":4.25},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"x-ai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":450000},"cost":{"input":1.6,"output":4.8},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":450000},"cost":{"input":2,"output":6},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":117964},"cost":{"input":0.119,"output":0.3},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B","type":"chat"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["audio","image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.35,"output":6.75},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["audio","image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"mistralai/mistral-nemo","name":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.165,"output":0.17},"canonical_model_id":"mistral/mistral-nemo","display_name":"Mistral Nemo","type":"chat"},{"id":"mistralai/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.165,"output":0.66},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"mistralai/mistral-large-2512","name":"Mistral Large 3 2512","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":209715},"cost":{"input":0.5,"output":1.5},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3 2512","type":"chat"},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-01-31","release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":52428},"cost":{"input":2.2,"output":6.6},"canonical_model_id":"mistral/mixtral-8x22b-instruct","display_name":"Mixtral 8x22B Instruct","type":"chat"},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":943718},"cost":{"input":3.45,"output":17.25},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.6,"output":2.5},"canonical_model_id":"moonshotai/kimi-k2-0905","display_name":"Kimi K2 0905","type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.3,"output":1.5},"canonical_model_id":"alibaba/qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":235929},"cost":{"input":0.3,"output":1.5},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","family":"qwen","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-10-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.2,"output":0.7},"canonical_model_id":"alibaba/qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","type":"chat"},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2.5,"output":15},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":30,"output":180},"canonical_model_id":"openai/gpt-5.4-pro","display_name":"GPT-5.4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.2,"output":1.25},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"openai/gpt-5.6-sol-pro","name":"GPT-5.6 Sol Pro","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol Pro","type":"chat"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14},"canonical_model_id":"openai/gpt-5.3-codex","display_name":"GPT-5.3-Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 Nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 Nano","type":"chat"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.05,"output":0.4},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":10},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":10,"output":50},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.6-luna-pro","name":"GPT-5.6 Luna Pro","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":1,"output":6},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna Pro","type":"chat"},{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o-mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o-mini","type":"chat"},{"id":"openai/gpt-oss-20b","name":"gpt-oss-20b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.3},"canonical_model_id":"openai/gpt-oss-20b","display_name":"gpt-oss-20b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0.2,"output":1.2},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14},"canonical_model_id":"openai/gpt-5.2","display_name":"GPT-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 Mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 Mini","type":"chat"},{"id":"openai/gpt-5.6-terra-pro","name":"GPT-5.6 Terra Pro","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2.5,"output":15},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra Pro","type":"chat"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0.1,"output":0.5},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2.5,"output":15},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-120b","name":"gpt-oss-120b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.35,"output":0.75},"canonical_model_id":"openai/gpt-oss-120b","display_name":"gpt-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":5,"output":30},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":10},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"klokintegration":{"id":"klokintegration","api":"https://api-gw.klok.ipaas.se/proxy/kloker-key/v1","name":"klokintegration.se","doc":"https://klokintegration.se/docs/ai-api","display_name":"klokintegration.se","models":[{"id":"Kloker-Integration-Developer","name":"Kloker Integration Developer","description":"Knows the customer integration environment and Klok best practices. Opinionated about implementation. The gateway runs ecosystem lookup tools server-side and appends a system-prompt injection. Client system prompts and OpenAI tool calls are preserved.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-29","last_updated":"2026-08-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":50000},"status":"beta","cost":{"input":0.23,"output":1.16},"display_name":"Kloker Integration Developer","type":"chat"},{"id":"Kloker","name":"Kloker","description":"Cheap general model with a clean context. Nothing from the customer environment is packed in. It tracks the current best open source model. The Klok team verifies it and upgrades it periodically.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-29","last_updated":"2026-08-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":50000},"status":"beta","cost":{"input":0.23,"output":1.16},"display_name":"Kloker","type":"chat"},{"id":"Kloker-Integration-Architect","name":"Kloker Integration Architect","description":"Knows the customer integration environment and Klok best practices. Opinionated about structure. The gateway runs ecosystem lookup tools server-side and appends a system-prompt injection (data contracts, CloudEvents, event-driven flows). Client system prompts and OpenAI tool calls are preserved.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-29","last_updated":"2026-08-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":50000},"status":"beta","cost":{"input":0.23,"output":1.16},"display_name":"Kloker Integration Architect","type":"chat"}]},"google-vertex":{"id":"google-vertex","name":"Vertex","doc":"https://cloud.google.com/vertex-ai/generative-ai/docs/models","display_name":"Vertex","models":[{"id":"claude-opus-4-8@default","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gemini-2.5-flash-tts","name":"Gemini 2.5 Flash TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-09-30","last_updated":"2025-12-10","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":32768,"input":8192,"output":16384},"cost":{"input":0.5,"output":10},"canonical_model_id":"google/gemini-2.5-flash-tts","display_name":"Gemini 2.5 Flash TTS","type":"chat"},{"id":"claude-sonnet-4-5@20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-5-20250929","display_name":"Claude Sonnet 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30},"canonical_model_id":"google/gemini-2.5-flash-image","display_name":"Nano Banana","type":"image-generation"},{"id":"claude-opus-4-6@default","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-4@20250514","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-20250514","display_name":"Claude Opus 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-5-5@default","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"claude-opus-5-5@default","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-opus-5@default","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat"},{"id":"claude-sonnet-4-6@default","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-haiku-4-5@20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":60,"cache_read":0.05},"canonical_model_id":"google/gemini-3.1-flash-image","display_name":"Nano Banana 2","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"codestral-2","name":"Codestral 2","description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"provider":{"npm":"@ai-sdk/mistral","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/publishers/mistralai/models"},"cost":{"input":0.3,"output":0.9},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 2","type":"chat"},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"beta","cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-opus-4-1@20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"canonical_model_id":"anthropic/claude-opus-4-1-20250805","display_name":"Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-4-5@20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-5-20251101","display_name":"Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-opus-4-7@default","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":120,"cache_read":0.2},"canonical_model_id":"google/gemini-3-pro-image","display_name":"Nano Banana Pro","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":30,"cache_read":0.025},"canonical_model_id":"google/gemini-3.1-flash-lite-image","display_name":"Nano Banana 2 Lite","type":"image-generation","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-fable-5-1@default","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"mistral-medium-3","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"provider":{"npm":"@ai-sdk/mistral","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/publishers/mistralai/models"},"cost":{"input":0.4,"output":2},"canonical_model_id":"mistral/mistral-medium-2505","display_name":"Mistral Medium 3","type":"chat"},{"id":"mistral-small-2503","name":"Mistral Small 3.1 24B","description":"Efficient multimodal model for instruction following, coding, reasoning, and function calling","family":"mistral-small","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/mistral","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/publishers/mistralai/models"},"cost":{"input":0.1,"output":0.3},"canonical_model_id":"mistral/mistral-small-3-1-24b-instruct-2503","display_name":"Mistral Small 3.1 24B","type":"chat"},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"beta","cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"google/gemini-3.1-pro-preview-customtools","display_name":"Gemini 3.1 Pro Preview Custom Tools","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"beta","cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-fable-5@default","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-haiku-5-5@default","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"gemini-2.5-pro-tts","name":"Gemini 2.5 Pro TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-pro","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-09-30","last_updated":"2025-12-10","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":32768,"input":8192,"output":16384},"cost":{"input":1,"output":20},"canonical_model_id":"google/gemini-2.5-pro-tts","display_name":"Gemini 2.5 Pro TTS","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":1},"cost":{"input":0.15,"output":0},"canonical_model_id":"google/gemini-embedding-001","display_name":"Gemini Embedding 001","type":"embedding"},{"id":"claude-sonnet-4@20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-20250514","display_name":"Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gemini-nano-banana-2.1","name":"Nano Banana 2.1","description":"Image model for prompt-driven generation, multi-turn editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image","video"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":1.5,"output":30,"cache_read":0.15},"canonical_model_id":"google/gemini-nano-banana-2.1","display_name":"Nano Banana 2.1","type":"image-generation"},{"id":"claude-sonnet-5@default","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat"},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1,"input_audio":2},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/llama-4-maverick-17b-128e-instruct-maas","name":"Llama 4 Maverick 17B 128E Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":8192},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.35,"output":1.15},"display_name":"Llama 4 Maverick 17B 128E Instruct","type":"chat"},{"id":"meta/llama-4-scout-17b-16e-instruct-maas","name":"Llama 4 Scout 17B Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1310720,"output":8192},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.25,"output":0.7},"canonical_model_id":"meta/llama-4-scout-17b-instruct","display_name":"Llama 4 Scout 17B Instruct","type":"chat"},{"id":"meta/llama-3.3-70b-instruct-maas","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.72,"output":0.72},"display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"google/gemma-4-26b-a4b-it-maas","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"status":"alpha","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xai/grok-4.20-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-reasoning","display_name":"Grok 4.20 (Reasoning)","type":"chat"},{"id":"xai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":500000},"status":"beta","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"xai/grok-4.20-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.20-0309-non-reasoning","display_name":"Grok 4.20 (Non-Reasoning)","type":"chat"},{"id":"xai/grok-4.1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":30000},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"xai/grok-4.1-fast-reasoning","display_name":"Grok 4.1 Fast (Reasoning)","type":"chat"},{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":30000},"status":"beta","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.1-fast-non-reasoning","name":"Grok 4.1 Fast","description":"Fast Grok model for responsive chat, tool-assisted work, and low-latency responses","family":"grok","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":30000},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"canonical_model_id":"xai/grok-4.1-fast","display_name":"Grok 4.1 Fast","type":"chat"},{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":500000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/deepseek-v3.1-maas","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.6,"output":1.7,"cache_read":0.06},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek-ai/deepseek-v3.2-maas","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-17","last_updated":"2026-04-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.56,"output":1.68,"cache_read":0.056},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2-thinking-maas","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.6,"output":2.5,"cache_read":0.06},"display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-5-maas","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":1,"output":3.2,"cache_read":0.1},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-4.7-maas","name":"GLM-4.7","description":"GLM model for coding, tool use, and complex reasoning","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-06","last_updated":"2026-01-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.6,"output":2.2,"cache_read":0.06},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-5.2-maas","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"status":"beta","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-235b-a22b-instruct-2507-maas","name":"Qwen3 235B A22B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.22,"output":0.88},"display_name":"Qwen3 235B A22B Instruct","type":"chat"},{"id":"openai/gpt-oss-20b-maas","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.07,"output":0.25,"cache_read":0.007},"display_name":"GPT OSS 20B","type":"chat"},{"id":"openai/gpt-oss-120b-maas","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.09,"output":0.36},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat"}]},"evroc":{"id":"evroc","api":"https://models.think.evroc.com/v1","name":"evroc","doc":"https://docs.evroc.com/products/think/overview.html","display_name":"evroc","models":[{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.144,"output":0.575},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"intfloat/multilingual-e5-large-instruct","name":"E5 Multi-Lingual Large Embeddings 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":512},"cost":{"input":0.114,"output":0.114},"display_name":"E5 Multi-Lingual Large Embeddings 0.6B","type":"chat"},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8-27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.87,"output":3.5},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8-27B","type":"chat"},{"id":"Qwen/Qwen3-Reranker-4B","name":"Qwen3 Reranker 4B","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.0575,"output":0},"display_name":"Qwen3 Reranker 4B","type":"rerank"},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.345,"output":1.38},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":4096},"cost":{"input":0.115,"output":0.115},"display_name":"Qwen3 Embedding 8B","type":"embedding"},{"id":"mistralai/Mistral-Medium-3.5-128B","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.725,"output":6.9},"canonical_model_id":"mistral/mistral-medium-2604","display_name":"Mistral Medium 3.5","type":"chat"},{"id":"mistralai/Voxtral-Small-24B-2507","name":"Voxtral Small 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"voxtral","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["audio","text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"display_name":"Voxtral Small 24B","type":"chat"},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.4375,"output":5.75},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":131072},"cost":{"input":1.4375,"output":5.75},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nvidia/Llama-3.3-70B-Instruct-FP8","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":1.15,"output":1.15},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"KBLab/kb-whisper-large","name":"KB Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":448},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"display_name":"KB Whisper","type":"chat"},{"id":"evroc/roc","name":"roc","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-06-06","last_updated":"2026-06-06","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":2.875,"output":11.516},"display_name":"roc","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai/whisper-large-v3","name":"Whisper 3 Large","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":4096},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"canonical_model_id":"openai/whisper-large-v3","display_name":"Whisper 3 Large","type":"chat"},{"id":"openai/whisper-large-v3-turbo","name":"Whisper Large v3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":448},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"canonical_model_id":"openai/whisper-large-v3-turbo","display_name":"Whisper Large v3 Turbo","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.23,"output":0.92},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"tokengo":{"id":"tokengo","api":"https://api.tokengo.com/v1","name":"TokenGo","doc":"https://www.tokengo.com/docs","display_name":"TokenGo","models":[{"id":"deepseek/deepseek-v3.1","name":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.19,"output":0.71,"cache_read":0.06},"canonical_model_id":"deepseek/deepseek-v3.1","display_name":"DeepSeek-V3.1","type":"chat"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":0.2174,"output":0.326,"cache_read":0.06},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.098,"output":0.196,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.075,"output":0.025,"cache_read":0.015},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.89,"output":3.2647,"cache_read":0.2226},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":2.65,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"submodel":{"id":"submodel","api":"https://llm.submodel.ai/v1","name":"submodel","doc":"https://submodel.gitbook.io","display_name":"submodel","models":[{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.2,"output":0.6},"display_name":"Qwen3 235B A22B Thinking 2507","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.2,"output":0.3},"display_name":"Qwen3 235B A22B Instruct 2507","type":"chat"},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.8},"display_name":"Qwen3 Coder 480B A35B Instruct","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":75000,"output":163840},"cost":{"input":0.2,"output":0.8},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":75000,"output":163840},"cost":{"input":0.5,"output":2.15},"display_name":"DeepSeek R1 0528","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":75000,"output":163840},"cost":{"input":0.2,"output":0.8},"display_name":"DeepSeek V3 0324","type":"chat"},{"id":"zai-org/GLM-4.5-FP8","name":"GLM 4.5 FP8","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.2,"output":0.8},"display_name":"GLM 4.5 FP8","type":"chat"},{"id":"zai-org/GLM-4.5-Air","name":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.5},"display_name":"GLM 4.5 Air","type":"chat"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.5},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"kosmik":{"id":"kosmik","api":"https://api.koscompute.com/v1","name":"Kosmik Compute","doc":"https://api.koscompute.com/docs/","display_name":"Kosmik Compute","models":[{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.35,"output":2.2,"cache_read":0.09},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"tencent-token-plan":{"id":"tencent-token-plan","api":"https://api.lkeap.cloud.tencent.com/plan/v3","name":"Tencent Token Plan","doc":"https://cloud.tencent.com/document/product/1823/130060","display_name":"Tencent Token Plan","models":[{"id":"hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":192000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":64000},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"togetherai":{"id":"togetherai","name":"Together AI","doc":"https://docs.together.ai/docs/serverless-models","display_name":"Together AI","models":[{"id":"meta-models/Muse-Spark-Open-816B-A42B","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"Llama 3.3 70B","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":1.04,"output":1.04},"display_name":"Llama 3.3 70B","type":"chat"},{"id":"reflection/Beam-1.0-501B-A23B","name":"Beam 1.0 501B A23B","description":"Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows","family":"beam","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-06-30","release_date":"2026-10-05","last_updated":"2026-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.4,"output":1.2,"cache_read":0.04},"canonical_model_id":"reflection/beam-1.0-501b-a23b","display_name":"Beam 1.0 501B A23B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["max","xhigh","high","medium","low","none"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":131072},"cost":{"input":1,"output":4.05,"cache_read":0.17},"canonical_model_id":"thinkingmachines/inkling","display_name":"Inkling","type":"chat"},{"id":"essentialai/Rnj-1-Instruct","name":"Rnj-1 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"rnj","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-05","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"status":"deprecated","cost":{"input":0.15,"output":0.15},"display_name":"Rnj-1 Instruct","type":"chat"},{"id":"Qwen/Qwen3.7-Max","name":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":500000},"cost":{"input":1.25,"output":3.75,"cache_read":0.125},"display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/Qwen2.5-7B-Instruct-Turbo","name":"Qwen 2.5 7B Instruct Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":0.3},"display_name":"Qwen 2.5 7B Instruct Turbo","type":"chat"},{"id":"Qwen/Qwen3-Coder-Next-FP8","name":"Qwen3 Coder Next FP8","description":"Legacy model retained for compatibility with older integrations","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2026-02-03","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.5,"output":1.2},"display_name":"Qwen3 Coder Next FP8","type":"chat"},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507-tput","name":"Qwen3 235B A22B Instruct 2507 FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.2,"output":0.6},"display_name":"Qwen3 235B A22B Instruct 2507 FP8","type":"chat"},{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.17,"output":0.25},"display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":130000},"status":"deprecated","cost":{"input":0.6,"output":3.6,"cache_read":0.35},"display_name":"Qwen3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","name":"Qwen3 Coder 480B A35B Instruct","description":"Legacy model retained for compatibility with older integrations","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":2,"output":2},"display_name":"Qwen3 Coder 480B A35B Instruct","type":"chat"},{"id":"Qwen/Qwen3.6-Plus","name":"Qwen3.6 Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":500000},"cost":{"input":0.5,"output":3},"display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"LiquidAI/LFM2-24B-A2B","name":"LFM2-24B-A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"liquid","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.03,"output":0.12},"display_name":"LFM2-24B-A2B","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek-R1","description":"Legacy model retained for compatibility with older integrations","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163839,"output":163839},"status":"deprecated","cost":{"input":3,"output":7},"display_name":"DeepSeek-R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.13},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-ai/DeepSeek-V3-1","name":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0.6,"output":1.7},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"Legacy model retained for compatibility with older integrations","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-12-26","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":1.25,"output":1.25},"display_name":"DeepSeek-V3","type":"chat"},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":250000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-11","release_date":"2026-04-07","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"status":"deprecated","cost":{"input":1.4,"output":4.4,"cache_read":0.26},"display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":164000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"status":"deprecated","cost":{"input":1,"output":3.2},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":400000},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/GLM-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","name":"Nemotron 3.5 Super VL 120B A12B","description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":0.5,"cache_read":0.02},"canonical_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","display_name":"Nemotron 3.5 Super VL 120B A12B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512300,"output":512300},"cost":{"input":0.6,"output":3.6,"cache_read":0.2},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.15,"output":0.6},"display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"helicone":{"id":"helicone","api":"https://ai-gateway.helicone.ai/v1","name":"Helicone","doc":"https://helicone.ai/models","display_name":"Helicone","models":[{"id":"grok-4-1-fast-reasoning","name":"xAI Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-17","last_updated":"2025-11-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"display_name":"xAI Grok 4.1 Fast Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-3","name":"xAI Grok 3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.75},"display_name":"xAI Grok 3","type":"chat"},{"id":"llama-4-scout","name":"Meta Llama 4 Scout 17B 16E","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.08,"output":0.3},"display_name":"Meta Llama 4 Scout 17B 16E","type":"chat"},{"id":"llama-guard-4","name":"Meta Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":1024},"cost":{"input":0.21,"output":0.21},"display_name":"Meta Llama Guard 4 12B","type":"chat"},{"id":"mistral-large-2411","name":"Mistral-Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-24","last_updated":"2024-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":6},"display_name":"Mistral-Large","type":"chat"},{"id":"grok-4-1-fast-non-reasoning","name":"xAI Grok 4.1 Fast Non-Reasoning","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-17","last_updated":"2025-11-17","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"display_name":"xAI Grok 4.1 Fast Non-Reasoning","type":"chat"},{"id":"qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":0.3,"output":1.5},"display_name":"Qwen3 VL 235B A22B Instruct","type":"chat"},{"id":"mistral-nemo","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16400},"cost":{"input":20,"output":40},"display_name":"Mistral Nemo","type":"chat"},{"id":"gpt-5.1-codex","name":"OpenAI: GPT-5.1 Codex","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"display_name":"OpenAI: GPT-5.1 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3-pro-preview","name":"Google Gemini 3 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.19999999999999998},"display_name":"Google Gemini 3 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-4o","name":"OpenAI GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-05","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"display_name":"OpenAI GPT-4o","type":"chat"},{"id":"gpt-4.1-mini-2025-04-14","name":"OpenAI GPT-4.1 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999},"display_name":"OpenAI GPT-4.1 Mini","type":"chat"},{"id":"glm-4.6","name":"Zai GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.44999999999999996,"output":1.5},"display_name":"Zai GLM-4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-3.5-haiku","name":"Anthropic: Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":0.7999999999999999,"output":4,"cache_read":0.08,"cache_write":1},"display_name":"Anthropic: Claude 3.5 Haiku","type":"chat"},{"id":"o1-mini","name":"OpenAI: o1-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":65536},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"OpenAI: o1-mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4","name":"xAI Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-09","last_updated":"2024-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":3,"output":15,"cache_read":0.75},"display_name":"xAI Grok 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-codex","name":"OpenAI: GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"display_name":"OpenAI: GPT-5 Codex","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"llama-4-maverick","name":"Meta Llama 4 Maverick 17B 128E","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.6},"display_name":"Meta Llama 4 Maverick 17B 128E","type":"chat"},{"id":"qwen3-coder","name":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.22,"output":0.95},"display_name":"Qwen3 Coder 480B A35B Instruct Turbo","type":"chat"},{"id":"gpt-5-mini","name":"OpenAI GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.024999999999999998},"display_name":"OpenAI GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o4-mini","name":"OpenAI o4 Mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"display_name":"OpenAI o4 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3-mini","name":"OpenAI o3 Mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2023-10","release_date":"2023-10-01","last_updated":"2023-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"OpenAI o3 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"kimi-k2-0711","name":"Kimi K2 (07/11)","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.5700000000000001,"output":2.3},"display_name":"Kimi K2 (07/11)","type":"chat"},{"id":"gpt-4.1-nano","name":"OpenAI GPT-4.1 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.024999999999999998},"display_name":"OpenAI GPT-4.1 Nano","type":"chat"},{"id":"grok-4-fast-reasoning","name":"xAI: Grok 4 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"display_name":"xAI: Grok 4 Fast Reasoning","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":40960},"cost":{"input":0.29,"output":0.59},"display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5-nano","name":"OpenAI GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.005},"display_name":"OpenAI GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-3.5-sonnet-v2","name":"Anthropic: Claude 3.5 Sonnet v2","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"display_name":"Anthropic: Claude 3.5 Sonnet v2","type":"chat"},{"id":"gpt-5.1-chat-latest","name":"OpenAI GPT-5.1 Chat","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"display_name":"OpenAI GPT-5.1 Chat","type":"chat"},{"id":"claude-4.5-sonnet","name":"Anthropic: Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"display_name":"Anthropic: Claude Sonnet 4.5","type":"chat"},{"id":"deepseek-tng-r1t2-chimera","name":"DeepSeek TNG R1T2 Chimera","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-02","last_updated":"2025-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":130000,"output":163840},"cost":{"input":0.3,"output":1.2},"display_name":"DeepSeek TNG R1T2 Chimera","type":"chat"},{"id":"deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.56,"output":1.68,"cache_read":0.07},"display_name":"DeepSeek V3","type":"chat"},{"id":"deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.03,"output":0.13},"display_name":"DeepSeek R1 Distill Llama 70B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"o1","name":"OpenAI: o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"display_name":"OpenAI: o1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mistral-small","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.075,"output":0.2},"canonical_model_id":"mistral/mistral-small-2506","display_name":"Mistral Small 3.2","type":"chat"},{"id":"chatgpt-4o-latest","name":"OpenAI ChatGPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-08-14","last_updated":"2024-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":5,"output":20,"cache_read":2.5},"display_name":"OpenAI ChatGPT-4o","type":"chat"},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.09999999999999999,"output":0.3},"display_name":"Qwen3 Coder 30B A3B Instruct","type":"chat"},{"id":"sonar-pro","name":"Perplexity Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":3,"output":15},"display_name":"Perplexity Sonar Pro","type":"chat"},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":262144},"cost":{"input":0.48,"output":2},"display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-4-fast-non-reasoning","name":"xAI Grok 4 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-19","last_updated":"2025-09-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"display_name":"xAI Grok 4 Fast Non-Reasoning","type":"chat"},{"id":"claude-opus-4-1-20250805","name":"Anthropic: Claude Opus 4.1 (20250805)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Anthropic: Claude Opus 4.1 (20250805)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5-pro","name":"OpenAI: GPT-5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":15,"output":120},"display_name":"OpenAI: GPT-5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-chat-latest","name":"OpenAI GPT-5 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":false,"knowledge":"2024-09","release_date":"2024-09-30","last_updated":"2024-09-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"display_name":"OpenAI GPT-5 Chat Latest","type":"chat"},{"id":"deepseek-v3.1-terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.27,"output":1,"cache_read":0.21600000000000003},"display_name":"DeepSeek V3.1 Terminus","type":"chat"},{"id":"claude-opus-4-1","name":"Anthropic: Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Anthropic: Claude Opus 4.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.1","name":"OpenAI GPT-5.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":false,"reasoning":{"supported":true,"default":false},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"display_name":"OpenAI GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"llama-3.3-70b-versatile","name":"Meta Llama 3.3 70B Versatile","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32678},"cost":{"input":0.59,"output":0.7899999999999999},"display_name":"Meta Llama 3.3 70B Versatile","type":"chat"},{"id":"llama-3.3-70b-instruct","name":"Meta Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16400},"cost":{"input":0.13,"output":0.39},"display_name":"Meta Llama 3.3 70B Instruct","type":"chat"},{"id":"grok-3-mini","name":"xAI Grok 3 Mini","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":0.5,"cache_read":0.075},"display_name":"xAI Grok 3 Mini","type":"chat"},{"id":"gemma-3-12b-it","name":"Google Gemma 3 12B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.049999999999999996,"output":0.09999999999999999},"display_name":"Google Gemma 3 12B","type":"chat"},{"id":"qwen2.5-coder-7b-fast","name":"Qwen2.5 Coder 7B fast","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-15","last_updated":"2024-09-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"cost":{"input":0.03,"output":0.09},"display_name":"Qwen2.5 Coder 7B fast","type":"chat"},{"id":"gpt-4o-mini","name":"OpenAI GPT-4o-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"display_name":"OpenAI GPT-4o-mini","type":"chat"},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":16384},"cost":{"input":0.14,"output":1.4},"display_name":"Qwen3 Next 80B A3B Instruct","type":"chat"},{"id":"o3-pro","name":"OpenAI o3 Pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"display_name":"OpenAI o3 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-oss-20b","name":"OpenAI GPT-OSS 20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.049999999999999996,"output":0.19999999999999998},"display_name":"OpenAI GPT-OSS 20b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-pro","name":"Google Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.3125,"cache_write":1.25},"display_name":"Google Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"sonar-deep-research","name":"Perplexity Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":2,"output":8},"display_name":"Perplexity Sonar Deep Research","type":"chat"},{"id":"gemini-2.5-flash","name":"Google Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.3},"display_name":"Google Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-4.5-haiku","name":"Anthropic: Claude 4.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"display_name":"Anthropic: Claude 4.5 Haiku","type":"chat"},{"id":"gemma2-9b-it","name":"Google Gemma 2","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-25","last_updated":"2024-06-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.01,"output":0.03},"display_name":"Google Gemma 2","type":"chat"},{"id":"claude-3.7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":{"supported":true,"default":false},"tool_call":true,"temperature":true,"knowledge":"2025-02","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"display_name":"Anthropic: Claude 3.7 Sonnet","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"hermes-2-pro-llama-3-8b","name":"Hermes 2 Pro Llama 3 8B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-05","release_date":"2024-05-27","last_updated":"2024-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.14,"output":0.14},"display_name":"Hermes 2 Pro Llama 3 8B","type":"chat"},{"id":"claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"display_name":"Anthropic: Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"qwen3-235b-a22b-thinking","name":"Qwen3 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":81920},"cost":{"input":0.3,"output":2.9000000000000004},"display_name":"Qwen3 235B A22B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-code-fast-1","name":"xAI Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-08-25","last_updated":"2024-08-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":10000},"cost":{"input":0.19999999999999998,"output":1.5,"cache_read":0.02},"display_name":"xAI Grok Code Fast 1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-sonnet-4-5-20250929","name":"Anthropic: Claude Sonnet 4.5 (20250929)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"display_name":"Anthropic: Claude Sonnet 4.5 (20250929)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-4.1","name":"OpenAI GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"OpenAI GPT-4.1","type":"chat"},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":41000,"output":41000},"cost":{"input":0.08,"output":0.29},"display_name":"Qwen3 30B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2-0905","name":"Kimi K2 (09/05)","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.5,"output":2,"cache_read":0.39999999999999997},"display_name":"Kimi K2 (09/05)","type":"chat"},{"id":"llama-3.1-8b-instruct","name":"Meta Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"cost":{"input":0.02,"output":0.049999999999999996},"display_name":"Meta Llama 3.1 8B Instruct","type":"chat"},{"id":"llama-3.1-8b-instruct-turbo","name":"Meta Llama 3.1 8B Instruct Turbo","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.02,"output":0.03},"display_name":"Meta Llama 3.1 8B Instruct Turbo","type":"chat"},{"id":"llama-prompt-guard-2-86m","name":"Meta Llama Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":512,"output":2},"cost":{"input":0.01,"output":0.01},"display_name":"Meta Llama Prompt Guard 2 86M","type":"chat"},{"id":"claude-haiku-4-5-20251001","name":"Anthropic: Claude 4.5 Haiku (20251001)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":{"supported":true,"default":false},"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"display_name":"Anthropic: Claude 4.5 Haiku (20251001)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"sonar","name":"Perplexity Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":1,"output":1},"display_name":"Perplexity Sonar","type":"chat"},{"id":"deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true},"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.56,"output":1.68,"cache_read":0.07},"display_name":"DeepSeek Reasoner","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-4.1-mini","name":"OpenAI GPT-4.1 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999},"display_name":"OpenAI GPT-4.1 Mini","type":"chat"},{"id":"ernie-4.5-21b-a3b-thinking","name":"Baidu Ernie 4.5 21B A3B Thinking","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ernie","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-03","release_date":"2025-03-16","last_updated":"2025-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8000},"cost":{"input":0.07,"output":0.28},"display_name":"Baidu Ernie 4.5 21B A3B Thinking","type":"chat"},{"id":"claude-4.5-opus","name":"Anthropic: Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Anthropic: Claude Opus 4.5","type":"chat"},{"id":"gemini-2.5-flash-lite","name":"Google Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.024999999999999998,"cache_write":0.09999999999999999},"display_name":"Google Gemini 2.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-3-haiku-20240307","name":"Anthropic: Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2024-03-07","last_updated":"2024-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"display_name":"Anthropic: Claude 3 Haiku","type":"chat"},{"id":"sonar-reasoning-pro","name":"Perplexity Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":2,"output":8},"display_name":"Perplexity Sonar Reasoning Pro","type":"chat"},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":0.41},"display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-prompt-guard-2-22m","name":"Meta Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":512,"output":2},"cost":{"input":0.01,"output":0.01},"display_name":"Meta Llama Prompt Guard 2 22M","type":"chat"},{"id":"gpt-oss-120b","name":"OpenAI GPT-OSS 120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.04,"output":0.16},"display_name":"OpenAI GPT-OSS 120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1 Codex Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","attachment":false,"reasoning":{"supported":true,"default":false},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.024999999999999998},"display_name":"OpenAI: GPT-5.1 Codex Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3","name":"OpenAI o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"OpenAI o3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5","name":"OpenAI GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"display_name":"OpenAI GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"llama-3.1-8b-instant","name":"Meta Llama 3.1 8B Instant","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32678},"cost":{"input":0.049999999999999996,"output":0.08},"display_name":"Meta Llama 3.1 8B Instant","type":"chat"},{"id":"sonar-reasoning","name":"Perplexity Sonar Reasoning","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":1,"output":5},"display_name":"Perplexity Sonar Reasoning","type":"chat"},{"id":"claude-opus-4","name":"Anthropic: Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Anthropic: Claude Opus 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}}]},"cortecs":{"id":"cortecs","api":"https://api.cortecs.ai/v1","name":"Cortecs","doc":"https://api.cortecs.ai/v1/models","display_name":"Cortecs","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2.898,"output":15.453,"cache_read":0.242},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.996,"output":4.982,"cache_read":0.099,"cache_write":1.186},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.179,"output":0.697},"canonical_model_id":"openai/gpt-oss-safeguard-120b","display_name":"GPT OSS Safeguard 120B","type":"chat"},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.223,"output":0.39},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":500000},"cost":{"input":0.1,"output":0.4,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Gemma 3 is a family of lightweight, multimodal models from Google, supporting text and image inputs, multilingual capabilities, and a 131K context window.","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":110000},"cost":{"input":0.099,"output":0.299},"canonical_model_id":"google/gemma-3-27b-it","display_name":"Gemma 3 27B IT","type":"chat"},{"id":"qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2.5,"output":6,"cache_read":0.625},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-large-2402","name":"mistral-large-2402","description":"Mistral Large (24.02) is Mistral AI’s most advanced language model, built for complex multilingual reasoning, code generation, and deep text understanding.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"cost":{"input":4.284,"output":12.952},"display_name":"mistral-large-2402","type":"chat"},{"id":"gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":2.659,"output":10.635,"cache_read":1.33},"canonical_model_id":"openai/gpt-4o","display_name":"GPT-4o","type":"chat"},{"id":"qwen3guard-gen-8b","name":"qwen3guard-gen-8b","description":"Qwen3Guard-Gen-8B is a large-scale multilingual safety moderation model designed for high-accuracy prompt and response classification.","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0,"output":0},"display_name":"qwen3guard-gen-8b","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.35,"cache_read":0.018},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ministral-8b-2512","name":"Ministral 3 8B 2512","description":"Ministral 3 8B is a balanced, efficient multimodal model offering strong text and vision capabilities, optimized for edge and local deployment.","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.179,"output":0.179,"cache_read":0.017},"canonical_model_id":"mistral/ministral-8b-2512","display_name":"Ministral 3 8B 2512","type":"chat"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.09,"output":0.17,"cache_read":0.014},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"mistral-7b-instruct-v0.2","name":"mistral-7b-instruct-v0.2","description":"Mistral 7B Instruct is a compact, 7B parameter model optimized for fast and efficient text and code generation with a 32K token context window.","attachment":true,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"cost":{"input":0.159,"output":0.219},"display_name":"mistral-7b-instruct-v0.2","type":"chat"},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.199,"output":0.598,"cache_read":0.018},"canonical_model_id":"alibaba/qwen3-235b-a22b-instruct-2507","display_name":"Qwen3 235B-A22B Instruct 2507","type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":14.999},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.167,"output":0.891},"canonical_model_id":"alibaba/qwen3-coder-next","display_name":"Qwen3 Coder Next","type":"chat"},{"id":"nova-lite-v1","name":"Nova Lite 1.0","description":"Nova Lite is a fast, low-cost multimodal foundation model capable of reasoning over text, images, and video in 200+ languages.","family":"nova-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.069,"output":0.275},"canonical_model_id":"amazon/nova-lite-v1","display_name":"Nova Lite 1.0","type":"chat"},{"id":"claude-haiku-5.5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.113,"output":0.563,"cache_read":0.011,"cache_write":0.14},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"apertus-70b","name":"Apertus 70B","description":"Apertus 70B is an open, multilingual language model designed for research, long-context reasoning, and sovereignty-focused AI systems.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":1.393,"output":2.228},"canonical_model_id":"swiss-ai/apertus-70b","display_name":"Apertus 70B","type":"chat"},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.279,"output":2.192,"cache_read":0.056},"canonical_model_id":"openai/gpt-5-mini","display_name":"GPT-5 Mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.201,"output":0.6,"cache_read":0.004},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.111,"output":0.434,"cache_read":0.056},"canonical_model_id":"openai/gpt-4.1-nano","display_name":"GPT-4.1 nano","type":"chat"},{"id":"minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196000,"output":196000},"cost":{"input":0.348,"output":1.39,"cache_read":0.075},"canonical_model_id":"minimax/MiniMax-M2.5","display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.179,"output":0.697},"canonical_model_id":"alibaba/qwen3-32b","display_name":"Qwen3 32B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistral-medium-3.5","name":"mistral-medium-3.5","description":"Mistral Medium 3.5 is a frontier multimodal 128B model combining reasoning, coding, and instruction-following with strong agentic performance and efficient deployment.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1.532,"output":7.843,"cache_read":0.154},"display_name":"mistral-medium-3.5","type":"chat"},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.06,"output":0.439,"cache_read":0.019},"canonical_model_id":"openai/gpt-5-nano","display_name":"GPT-5 Nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-4-6-sonnet","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.196,"output":15.94,"cache_read":0.32,"cache_write":3.999},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat"},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.475,"output":2.97,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"claude-4-5-sonnet","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":2.989,"output":14.945,"cache_read":0.326,"cache_write":4.078},"canonical_model_id":"anthropic/claude-sonnet-4-5","display_name":"Claude Sonnet 4.5 (latest)","type":"chat"},{"id":"devstral-2512","name":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.478,"output":2.392,"cache_read":0.045},"canonical_model_id":"mistral/devstral-2512","display_name":"Devstral 2","type":"chat"},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.038},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.179,"output":0.697,"cache_read":0.014},"canonical_model_id":"alibaba/qwen3-coder-30b-a3b-instruct","display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"mixtral-8x7B-instruct-v0.1","name":"Mixtral 8x7B Instruct v0.1","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.488,"output":0.758},"display_name":"Mixtral 8x7B Instruct v0.1","type":"chat"},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.4,"output":11.999,"cache_read":0.12,"cache_write":3},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":81920},"cost":{"input":0.111,"output":0.557},"canonical_model_id":"google/gemma-4-26b-a4b-it","display_name":"Gemma 4 26B A4B IT","type":"chat"},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.33,"output":2.749,"cache_read":0.033,"cache_write":0.082},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"voxtral-small-2507","name":"voxtral-small-2507","description":"Voxtral Small is a multimodal model with audio input, combining advanced speech capabilities with strong text performance for transcription, translation, and audio understanding.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-02-02","last_updated":"2026-02-02","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.123,"output":0.368,"cache_read":0.012},"display_name":"voxtral-small-2507","type":"chat"},{"id":"gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.375,"output":10.96,"cache_read":0.156},"canonical_model_id":"openai/gpt-5.1","display_name":"GPT-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.498,"cache_read":0.55,"cache_write":6.874},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.724,"output":0.724},"canonical_model_id":"meta/llama-3.3-70b-instruct","display_name":"Llama-3.3-70B-Instruct","type":"chat"},{"id":"qwen3guard-gen-0.6b","name":"qwen3guard-gen-0.6b","description":"Qwen3Guard-Gen-0.6B is a lightweight multilingual safety moderation model that classifies prompts and responses into safe, controversial, or unsafe categories.","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0,"output":0},"display_name":"qwen3guard-gen-0.6b","type":"chat"},{"id":"gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.159,"output":0.638,"cache_read":0.081},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":32768},"cost":{"input":0.167,"output":0.557},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"pixtral-12b-2409","name":"pixtral-12b-2409","description":"Pixtral 2409 12B is a state-of-the-art multimodal model with 12B parameters and a 400M vision encoder, natively trained on interleaved text and image data. It excels in tasks spanning vision-language reasoning, instruction following, and pure text understanding, making it highly effective for real-world multimodal applications.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2024-11-09","last_updated":"2024-11-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.223,"output":0.223},"display_name":"pixtral-12b-2409","type":"chat"},{"id":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.25,"output":11.249,"cache_read":0.225,"cache_write":2.813},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.045,"output":0.167},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.649,"output":9.899,"cache_read":0.165,"cache_write":1},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.495,"output":9.964,"cache_read":0.242,"cache_write":0.434},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"hermes-4-405b","name":"Hermes 4 405B","description":"Hermes 4 405B is a frontier hybrid-mode reasoning model built on Llama 3.1, optimized for advanced logic, math, coding, and structured output generation.","family":"hermes","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-08-31","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.996,"output":2.989},"canonical_model_id":"nousresearch/hermes-4-405b","display_name":"Hermes 4 405B","type":"chat"},{"id":"gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.299,"output":2.491,"cache_read":0.029,"cache_write":0.097},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen3-vl-235b-a22b","name":"qwen3-vl-235b-a22b","description":"Qwen3 VL 235B A22B is a 235B-parameter MoE vision-language flagship model (≈22B active) designed for frontier-level multimodal understanding across text, images, documents, and long videos.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-01-13","last_updated":"2026-01-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.617,"output":3.119,"cache_read":0.052},"display_name":"qwen3-vl-235b-a22b","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":2,"output":3.999,"cache_read":0.5},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":203000},"cost":{"input":0.08,"output":0.478},"canonical_model_id":"zhipuai/glm-4.7-flash","display_name":"GLM-4.7-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.111,"output":0.167},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.313,"output":26.561,"cache_read":0.531,"cache_write":6.645},"canonical_model_id":"anthropic/claude-opus-4-6","display_name":"Claude Opus 4.6","type":"chat"},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.219,"output":1.32,"cache_read":0.022,"cache_write":0.275},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.8-flash-next","name":"Qwen3.8 Flash Next","description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.201,"output":0.5,"cache_read":0.05},"canonical_model_id":"alibaba/qwen3.8-flash-next","display_name":"Qwen3.8 Flash Next","type":"chat"},{"id":"mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.156,"output":0.625,"cache_read":0.016},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat"},{"id":"nemotron-nano-v2-12b","name":"nemotron-nano-v2-12b","description":"NVIDIA Nemotron Nano v2 12B is a 12-billion-parameter multimodal reasoning model designed for advanced video understanding, document intelligence, and visual reasoning, built with a hybrid Transformer-Mamba architecture for high efficiency and low latency.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-10-31","last_updated":"2025-10-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.24,"output":0.707},"display_name":"nemotron-nano-v2-12b","type":"chat"},{"id":"mistral-small-2503","name":"mistral-small-2503","description":"Combines advanced text and vision capabilities with 24 billion parameters, supporting multilingual tasks and long contexts up to 131k tokens, making it versatile for various applications without sacrificing performance.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.111,"output":0.334},"display_name":"mistral-small-2503","type":"chat"},{"id":"gpt-4.1","name":"GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2.192,"output":8.769,"cache_read":0.546},"canonical_model_id":"openai/gpt-4.1","display_name":"GPT-4.1","type":"chat"},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.219,"cache_write":2.749},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.668,"output":4.01},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.038},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1000000},"cost":{"input":0.9,"output":3.24,"cache_read":0.189},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"pixtral-large-2502","name":"Pixtral Large (25.02)","description":"Pixtral Large (25.02) is a 124B open-weight multimodal model built on Mistral Large 2, offering advanced image understanding and strong performance across text and code tasks.","family":"pixtral","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-04-08","last_updated":"2025-04-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":1.993,"output":5.978},"canonical_model_id":"mistral/pixtral-large-2502","display_name":"Pixtral Large (25.02)","type":"chat"},{"id":"claude-opus4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.437,"output":27.186,"cache_read":0.544,"cache_write":6.797},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat"},{"id":"minicpm-v-4.5","name":"minicpm-v-4.5","description":"MiniCPM-V 4.5 is a compact, high-performance vision-language model excelling in video understanding, OCR, and multimodal reasoning with efficient deployment.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.651,"output":1.097},"display_name":"minicpm-v-4.5","type":"chat"},{"id":"glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.384,"output":4.348,"cache_read":0.346},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3-30b-a3b-instruct-2507","name":"qwen3-30b-a3b-instruct-2507","description":"Qwen3-30B-A3B-Instruct-2507 is an advanced Mixture-of-Experts model optimized for reasoning, coding, and multilingual instruction following.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.099,"output":0.299},"display_name":"qwen3-30b-a3b-instruct-2507","type":"chat"},{"id":"qwen2.5-vl-72b-instruct","name":"qwen2.5-vl-72b-instruct","description":"Qwen2.5-VL is a powerful vision-language model with advanced capabilities in visual understanding, long video reasoning, and structured output generation.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":false,"release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":1.014,"output":1.014},"display_name":"qwen2.5-vl-72b-instruct","type":"chat"},{"id":"mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.613,"output":1.838,"cache_read":0.061},"canonical_model_id":"mistral/mistral-large-2512","display_name":"Mistral Large 3","type":"chat"},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.434,"output":1.704,"cache_read":0.134},"canonical_model_id":"openai/gpt-4.1-mini","display_name":"GPT-4.1 mini","type":"chat"},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.825,"output":4.125,"cache_read":0.082,"cache_write":0.084},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"ministral-14b-2512","name":"Ministral 3 14B 2512","description":"Ministral 3 14B is a frontier-level 14B multimodal model optimized for local deployment, delivering state-of-the-art text and vision reasoning with a 256K context window and strong agentic capabilities.","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.24,"output":0.24,"cache_read":0.022},"canonical_model_id":"mistral/ministral-14b-2512","display_name":"Ministral 3 14B 2512","type":"chat"},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.12,"output":0.6,"cache_read":0.012,"cache_write":0.15},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.7,"output":3.4,"cache_read":0.15},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"mistral-large-4-0","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":262144},"cost":{"input":0.765,"output":2.351,"cache_read":0.079},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.399,"output":21.998,"cache_read":0.219,"cache_write":5.5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.446,"output":3.008},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.437,"output":27.186,"cache_read":0.544,"cache_write":6.797},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat"},{"id":"mistral-small-3.2-24b-instruct-2506","name":"mistral-small-3.2-24b-instruct-2506","description":"Mistral-Small-3.2-24B-Instruct-2506 is a 24B parameter instruction-tuned model with enhanced long-context support (128k) and state-of-the-art vision understanding.","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.1,"output":0.312},"display_name":"mistral-small-3.2-24b-instruct-2506","type":"chat"},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":13.199,"cache_read":0.219,"cache_write":2.749},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.5,"output":1.499,"cache_read":0.15},"canonical_model_id":"deepseek/deepseek-v3.2","display_name":"DeepSeek V3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nova-2-lite","name":"Nova 2 Lite","description":"Nova 2 Lite is an advanced multimodal reasoning model that combines efficiency and performance, delivering reliable AI for agentic workflows and enterprise applications.","family":"nova","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.373,"output":3.144},"canonical_model_id":"amazon/nova-2-lite","display_name":"Nova 2 Lite","type":"chat"},{"id":"nova-pro-v1","name":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":10000},"cost":{"input":0.918,"output":3.671},"canonical_model_id":"amazon/nova-pro-v1","display_name":"Nova Pro 1.0","type":"chat"},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.089,"output":0.446,"cache_read":0.01},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ministral-3b-2512","name":"Ministral 3 3B 2512","description":"Ministral 3 3B is a compact, efficient multimodal model with strong language, vision capabilities, and ideal for custom fine-tuning.","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.123,"output":0.123,"cache_read":0.012},"canonical_model_id":"mistral/ministral-3b-2512","display_name":"Ministral 3 3B 2512","type":"chat"},{"id":"claude-opus4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5.313,"output":26.568,"cache_read":0.531,"cache_write":6.645},"canonical_model_id":"anthropic/claude-opus-4-5","display_name":"Claude Opus 4.5 (latest)","type":"chat"},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.873,"output":3.306,"cache_read":0.221},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.656,"output":3.3,"cache_read":0.18},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.375,"output":10.96,"cache_read":0.156},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"minimax-m2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196000,"output":196000},"cost":{"input":0.359,"output":1.435},"canonical_model_id":"minimax/MiniMax-M2.1","display_name":"MiniMax-M2.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":0.511,"output":1.534,"cache_read":0.128},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","type":"chat"},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4.399,"output":21.998,"cache_read":0.44,"cache_write":5.5},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"mistral-nemo-instruct-2407","name":"mistral-nemo-instruct-2407","description":"A 12B parameter, instruct-tuned language model by Mistral AI and NVIDIA, designed for advanced instruction following, multi-turn conversations, and generating text and code across multiple languages.","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2024-08-07","last_updated":"2024-08-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.145,"output":0.145,"cache_read":0.014},"display_name":"mistral-nemo-instruct-2407","type":"chat"},{"id":"gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":2.25,"output":11.249,"cache_read":0.113},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"minimax-m2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":400000,"output":196000},"cost":{"input":0.349,"output":1.405},"canonical_model_id":"minimax/MiniMax-M2","display_name":"MiniMax-M2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"nova-micro-v1","name":"Nova Micro 1.0","description":"Nova Micro is a multilingual text-to-text foundation model with strong reasoning capabilities and broad language coverage across 200+ languages.","family":"nova-micro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":10000},"cost":{"input":0.04,"output":0.159},"canonical_model_id":"amazon/nova-micro-v1","display_name":"Nova Micro 1.0","type":"chat"},{"id":"codestral-2508","name":"Codestral 25.08","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.368,"output":1.103,"cache_read":0.037},"canonical_model_id":"mistral/codestral-2508","display_name":"Codestral 25.08","type":"chat"},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.4,"output":11.999,"cache_read":0.24,"cache_write":3},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"nvidia-nemotron-3-nano-30b-a3b","name":"nvidia-nemotron-3-nano-30b-a3b","description":"Nemotron-Nano-3-30B-A3B is a compact Mixture-of-Experts model optimized for efficient reasoning, chat, and coding, with strong multilingual support and long-context RAG and agent workflows.","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-01-12","last_updated":"2026-01-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.06,"output":0.24},"display_name":"nvidia-nemotron-3-nano-30b-a3b","type":"chat"},{"id":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.272,"output":1.631,"cache_read":0.025,"cache_write":0.082},"canonical_model_id":"google/gemini-3.1-flash-lite","display_name":"Gemini 3.1 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"agnes":{"id":"agnes","api":"https://apihub.agnes-ai.com/v1","name":"Agnes AI","doc":"https://agnes-ai.com/doc","display_name":"Agnes AI","models":[{"id":"agnes-2.5-pro-alpha","name":"Agnes 2.5 Pro Alpha","description":"Paid reasoning model for advanced coding, scientific reasoning, long-context analysis, agentic workflows, and multimodal understanding.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0.45,"output":0.9,"cache_read":0.0038},"display_name":"Agnes 2.5 Pro Alpha","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"agnes-3.0-flash","name":"Agnes 3.0 Flash","description":"A new-generation Agnes AI text model with stronger Agnes Code task execution, tool orchestration, and trustworthy delivery.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-09","last_updated":"2026-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":65536},"cost":{"input":0,"output":0},"display_name":"Agnes 3.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"agnes-2.0-flash","name":"Agnes 2.0 Flash","description":"Fast and efficient model for agent workflows, tool calling, coding, and image understanding.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-25","last_updated":"2026-05-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":65536},"status":"deprecated","cost":{"input":0,"output":0},"display_name":"Agnes 2.0 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"agnes-2.5-flash","name":"Agnes 2.5 Flash","description":"Upgraded model with improved coding, agent workflows, tool calling, and multimodal understanding.","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07","last_updated":"2026-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":65536},"cost":{"input":0,"output":0},"display_name":"Agnes 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"daoxe":{"id":"daoxe","api":"https://daoxe.com/v1","name":"DaoXE","doc":"https://daoxe.com/pricing","display_name":"DaoXE","models":[{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"canonical_model_id":"moonshotai/kimi-k2.5","display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":5},"canonical_model_id":"anthropic/claude-haiku-4-5-20251001","display_name":"Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}}]},"morph":{"id":"morph","api":"https://api.morphllm.com/v1","name":"Morph","doc":"https://docs.morphllm.com/api-reference/introduction","display_name":"Morph","models":[{"id":"morph-v3-large","name":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.9,"output":1.9},"display_name":"Morph v3 Large","type":"chat"},{"id":"morph-v3-fast","name":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":0.8,"output":1.2},"display_name":"Morph v3 Fast","type":"chat"},{"id":"auto","name":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":{"supported":true},"tool_call":false,"temperature":false,"release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.85,"output":1.55},"display_name":"Auto","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"openai":{"id":"openai","name":"OpenAI","doc":"https://platform.openai.com/docs/models","display_name":"OpenAI","models":[{"id":"chatgpt-image-latest","name":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":8192,"input":0,"output":8192},"display_name":"chatgpt-image-latest","type":"chat"},{"id":"gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"display_name":"GPT-5.4","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"display_name":"GPT-5.4 Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":{"supported":false},"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"status":"deprecated","cost":{"input":0.5,"output":1.5,"cache_read":0},"display_name":"GPT-3.5-turbo","type":"chat"},{"id":"gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"display_name":"GPT-5.5 Pro","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2024-01","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":1536},"cost":{"input":0.02,"output":0},"display_name":"text-embedding-3-small","type":"embedding"},{"id":"gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"flex":{"cost":{"input":0.1,"output":0.625,"cache_read":0.01},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"display_name":"GPT-5.4 nano","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-realtime-2.1","name":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text","audio","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"input":96000,"output":32000},"cost":{"input":4,"output":24,"cache_read":0.4,"input_audio":32,"output_audio":64},"canonical_model_id":"openai/gpt-realtime-2.1","display_name":"GPT-Realtime-2.1","type":"chat"},{"id":"gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","experimental":{"modes":{"fast":{"cost":{"input":8.75,"output":26.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":15},"display_name":"GPT-4o (2024-05-13)","type":"chat"},{"id":"gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"experimental":{"modes":{"fast":{"cost":{"input":4.25,"output":17,"cache_read":2.125},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":10,"cache_read":1.25},"display_name":"GPT-4o","type":"chat"},{"id":"gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":0.45,"output":3.6,"cache_read":0.045},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.125,"output":1,"cache_read":0.0125},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"GPT-5 Mini","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-image-2","name":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"input":0,"output":8192},"cost":{"input":5,"output":30,"cache_read":1.25},"canonical_model_id":"openai/gpt-image-2","display_name":"gpt-image-2","metadata":{"pricing":{"text_input":5,"text_cache_read":1.25,"image_input":8,"image_cache_read":2,"image_output":30,"unit":"USD per 1M tokens"}},"structured_output":false,"type":"image-generation"},{"id":"gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"display_name":"GPT-5.2 Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","experimental":{"modes":{"fast":{"cost":{"input":2,"output":8,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.55,"output":2.2,"cache_read":0.138},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"display_name":"o4-mini","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"o3-mini","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2022-12","release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.1,"output":0},"display_name":"text-embedding-ada-002","type":"embedding"},{"id":"gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"status":"deprecated","cost":{"input":30,"output":60},"display_name":"GPT-4","type":"chat"},{"id":"gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":28,"cache_read":0.35},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","experimental":{"modes":{"fast":{"cost":{"input":0.2,"output":0.8,"cache_read":0.05},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"display_name":"GPT-4.1 nano","type":"chat"},{"id":"gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"flex":{"cost":{"input":0.025,"output":0.2,"cache_read":0.0025},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"display_name":"GPT-5 Nano","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.6","name":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":8,"output":40,"cache_read":0.8,"cache_write":10},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.2-chat-latest","name":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2 Chat","type":"chat"},{"id":"o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"display_name":"o1","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"display_name":"GPT-5 Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-spark","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":100000,"output":32000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Codex Spark","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}},"ultrafast":{"cost":{"input":12,"output":60,"cache_read":0.6,"cache_write":15},"provider":{"body":{"service_tier":"ultrafast"}}}}},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2024-01","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.13,"output":0},"display_name":"text-embedding-3-large","type":"embedding"},{"id":"gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"display_name":"GPT-4o (2024-08-06)","type":"chat"},{"id":"gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":20,"output":100,"cache_read":2,"cache_write":25},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}},"ultrafast":{"cost":{"input":60,"output":300,"cache_read":6,"cache_write":75},"provider":{"body":{"service_tier":"ultrafast"}}}}},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":2.5,"output":20,"cache_read":0.25},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.625,"output":5,"cache_read":0.0625},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"experimental":{"modes":{"fast":{"cost":{"input":0.25,"output":1,"cache_read":0.125},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"display_name":"GPT-4o mini","type":"chat"},{"id":"o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"display_name":"o3-pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-image-1","name":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"input":0,"output":8192},"status":"deprecated","canonical_model_id":"openai/gpt-image-1","display_name":"gpt-image-1","type":"image-generation"},{"id":"gpt-daybreak-blue-latest","name":"Daybreak Blue","description":"Alias for flagship general-purpose models with safeguards for defensive cybersecurity work","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"Daybreak Blue","type":"chat"},{"id":"gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.375,"output":2.25,"cache_read":0.0375},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"display_name":"GPT-5.4 mini","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":28,"cache_read":0.35},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.875,"output":7,"cache_read":0.0875},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.2","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"display_name":"GPT-5.5","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":14,"cache_read":0.875},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"GPT-4.1","type":"chat"},{"id":"gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"display_name":"GPT-4o (2024-11-20)","type":"chat"},{"id":"gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"experimental":{"modes":{"fast":{"cost":{"input":0.7,"output":2.8,"cache_read":0.175},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"display_name":"GPT-4.1 mini","type":"chat"},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":0.2,"output":1,"cache_read":0.02,"cache_write":0.25},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"GPT-5.3 Chat (latest)","type":"chat"},{"id":"gpt-image-1-mini","name":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":8192,"input":0,"output":8192},"display_name":"gpt-image-1-mini","type":"image-generation"},{"id":"gpt-image-1.5","name":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":8192,"input":0,"output":8192},"canonical_model_id":"openai/gpt-image-1.5","display_name":"gpt-image-1.5","type":"image-generation"},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":4,"output":24,"cache_read":0.4,"cache_write":5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"display_name":"GPT-4 Turbo","type":"chat"},{"id":"gpt-daybreak-red-latest","name":"Daybreak Red","description":"Alias for advanced cybersecurity models for authorized vulnerability research and security testing","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":12.5,"output":75,"cache_read":1.25,"cache_write":15.625},"canonical_model_id":"openai/gpt-5.6-cyber","display_name":"Daybreak Red","type":"chat"},{"id":"o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"experimental":{"modes":{"fast":{"cost":{"input":3.5,"output":14,"cache_read":0.875},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":1,"output":4,"cache_read":0.25},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"o3","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":2.5,"output":20,"cache_read":0.25},"provider":{"body":{"service_tier":"priority"}}},"flex":{"cost":{"input":0.625,"output":5,"cache_read":0.0625},"provider":{"body":{"service_tier":"flex"}}}}},"cost":{"input":1.25,"output":10,"cache_read":0.125},"canonical_model_id":"openai/gpt-5","display_name":"GPT-5","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":8,"output":40,"cache_read":0.8,"cache_write":10},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":150,"output":600},"display_name":"o1-pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"}]},"alibaba-coding-plan-cn":{"id":"alibaba-coding-plan-cn","api":"https://coding.dashscope.aliyuncs.com/v1","name":"Alibaba Coding Plan (China)","doc":"https://help.aliyun.com/zh/model-studio/coding-plan","display_name":"Alibaba Coding Plan (China)","models":[{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3 Coder Next","type":"chat"},{"id":"qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3.5 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-max-2026-01-23","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":24576},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"MiniMax-M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"io-net":{"id":"io-net","api":"https://api.intelligence.io.solutions/api/v1","name":"IO.NET","doc":"https://io.net/docs/guides/intelligence/io-intelligence","display_name":"IO.NET","models":[{"id":"meta-llama/Llama-3.2-90B-Vision-Instruct","name":"Llama 3.2 90B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.35,"output":0.4,"cache_read":0.175,"cache_write":0.7},"display_name":"Llama 3.2 90B Vision Instruct","type":"chat"},{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.13,"output":0.38,"cache_read":0.065,"cache_write":0.26},"display_name":"Llama 3.3 70B Instruct","type":"chat"},{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"Llama 4 Maverick 17B 128E Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":430000,"output":4096},"cost":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.3},"display_name":"Llama 4 Maverick 17B 128E Instruct","type":"chat"},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen 3 Next 80B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-10","last_updated":"2025-01-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4096},"cost":{"input":0.1,"output":0.8,"cache_read":0.05,"cache_write":0.2},"display_name":"Qwen 3 Next 80B Instruct","type":"chat"},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen 3 235B Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4096},"cost":{"input":0.11,"output":0.6,"cache_read":0.055,"cache_write":0.22},"display_name":"Qwen 3 235B Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen 2.5 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.05,"output":0.22,"cache_read":0.025,"cache_write":0.1},"display_name":"Qwen 2.5 VL 32B Instruct","type":"chat"},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8.75,"cache_read":1,"cache_write":4},"display_name":"DeepSeek R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral Nemo Instruct 2407","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-05","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.02,"output":0.04,"cache_read":0.01,"cache_write":0.04},"display_name":"Mistral Nemo Instruct 2407","type":"chat"},{"id":"mistralai/Magistral-Small-2506","name":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-small","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.5,"output":1.5,"cache_read":0.25,"cache_write":1},"display_name":"Magistral Small 2506","type":"chat"},{"id":"mistralai/Devstral-Small-2505","name":"Devstral Small 2505","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-05-01","last_updated":"2025-05-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.05,"output":0.22,"cache_read":0.025,"cache_write":0.1},"display_name":"Devstral Small 2505","type":"chat"},{"id":"mistralai/Mistral-Large-Instruct-2411","name":"Mistral Large Instruct 2411","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":6,"cache_read":1,"cache_write":4},"display_name":"Mistral Large Instruct 2411","type":"chat"},{"id":"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","name":"Qwen 3 Coder 480B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":106000,"output":4096},"cost":{"input":0.22,"output":0.95,"cache_read":0.11,"cache_write":0.44},"display_name":"Qwen 3 Coder 480B","type":"chat"},{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.55,"output":2.25,"cache_read":0.275,"cache_write":1.1},"display_name":"Kimi K2 Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-09-05","last_updated":"2024-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.39,"output":1.9,"cache_read":0.195,"cache_write":0.78},"display_name":"Kimi K2 Instruct","type":"chat"},{"id":"zai-org/GLM-4.6","name":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-11-15","last_updated":"2024-11-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.4,"output":1.75,"cache_read":0.2,"cache_write":0.8},"display_name":"GLM 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-20b","name":"GPT-OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":4096},"cost":{"input":0.03,"output":0.14,"cache_read":0.015,"cache_write":0.06},"display_name":"GPT-OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"GPT-OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.04,"output":0.4,"cache_read":0.02,"cache_write":0.08},"display_name":"GPT-OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"infomaniak":{"id":"infomaniak","api":"https://api.infomaniak.com/2/ai/${INFOMANIAK_PRODUCT_ID}/openai/v1","name":"Infomaniak","doc":"https://www.infomaniak.com/en/hosting/ai-services/open-source-models","display_name":"Infomaniak","models":[{"id":"mini_lm_l12_v2","name":"All-MiniLM-L12-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2021-08-30","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128,"input":128,"output":384},"cost":{"input":0,"output":0},"display_name":"All-MiniLM-L12-v2","type":"chat"},{"id":"bge_multilingual_gemma2","name":"BGE Multilingual Gemma2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-07-25","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":8000,"output":3584},"cost":{"input":0.08,"output":0},"display_name":"BGE Multilingual Gemma2","type":"chat"},{"id":"swiss-ai/Apertus-v1.5-70B","name":"Apertus v1.5 70B","description":"Open, ethically-sourced Swiss AI model for multilingual, multimodal chat and instruction following","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-07-24","last_updated":"2026-08-01","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"input":100000,"output":8192},"status":"beta","cost":{"input":0.87,"output":3.1},"display_name":"Apertus v1.5 70B","type":"chat"},{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"input":100000,"output":32768},"cost":{"input":0.25,"output":0.5},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"Qwen/Qwen3.5-122B-A10B-FP8","name":"Qwen3.5 122B-A10B FP8","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65536},"cost":{"input":0.5,"output":3.97},"canonical_model_id":"alibaba/qwen3.5-122b-a10b","display_name":"Qwen3.5 122B-A10B FP8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3.5-397B-A17B-FP8","name":"Qwen3.5 397B-A17B FP8","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65536},"status":"beta","cost":{"input":0.99,"output":4.46},"canonical_model_id":"alibaba/qwen3.5-397b-a17b","display_name":"Qwen3.5 397B-A17B FP8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.25,"output":0.93},"canonical_model_id":"mistral/mistral-small-2603","display_name":"Mistral Small 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"mistralai/Ministral-3-14B-Instruct-2512","name":"Ministral 3 14B Instruct","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"input":100000,"output":25600},"status":"beta","cost":{"input":0.37,"output":0.5},"display_name":"Ministral 3 14B Instruct","type":"chat"},{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"status":"beta","cost":{"input":0.74,"output":3.72},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","name":"Nemotron 3 Nano 30B A3B FP8","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":262144},"status":"beta","cost":{"input":0.06,"output":0.25},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B FP8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}}]},"llmtech":{"id":"llmtech","api":"https://api.llmtech.eu/v1","name":"LLM Tech","doc":"https://llmtech.eu/models/qwen3.8-27b","display_name":"LLM Tech","models":[{"id":"nvidia/Qwen3.8-27B-NVFP4","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.25,"output":2.09,"cache_read":0.04},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"}]},"crossmodel":{"id":"crossmodel","api":"https://api.crossmodel.ai/v1","name":"CrossModel","doc":"https://www.crossmodel.ai/docs","display_name":"CrossModel","models":[{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"canonical_model_id":"anthropic/claude-haiku-4-5","display_name":"Claude Haiku 4.5 (latest)","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5","display_name":"Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-8","display_name":"Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Claude Sonnet 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"canonical_model_id":"anthropic/claude-sonnet-4-6","display_name":"Claude Sonnet 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-4-7","display_name":"Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.35,"output":4.05,"cache_read":0.045,"cache_write":1.35},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":0.3},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":192000,"output":131072},"cost":{"input":0.16,"output":0.64,"cache_read":0.04,"cache_write":0.16},"canonical_model_id":"tencent/hy3","display_name":"Hy3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy4-preview","name":"Hy4 preview","description":"A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.","family":"Hy","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-28","last_updated":"2026-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0.96,"output":2.88,"cache_read":0.048,"cache_write":0.96},"canonical_model_id":"tencent/hy4-preview","display_name":"Hy4 preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0.15},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":3,"cache_read":0.16,"cache_write":0.6,"tiers":[{"input":0.8,"output":3.4,"cache_read":0.2,"cache_write":0.8,"tier":{"type":"context","size":32000}}]},"canonical_model_id":"zhipuai/glm-5","display_name":"GLM-5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.47,"output":2.16,"cache_read":0.1,"cache_write":0.47,"tiers":[{"input":0.62,"output":2.47,"cache_read":0.13,"cache_write":0.62,"tier":{"type":"context","size":32000}}]},"canonical_model_id":"zhipuai/glm-4.7","display_name":"GLM-4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1,"output":3.8,"cache_read":0.2,"cache_write":1,"tiers":[{"input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2,"tier":{"type":"context","size":32000}}]},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.9,"output":3.7,"cache_read":0.18,"cache_write":0.9,"tiers":[{"input":1.1,"output":4.3,"cache_read":0.27,"cache_write":1.1,"tier":{"type":"context","size":32000}}]},"canonical_model_id":"zhipuai/glm-5-turbo","display_name":"GLM-5-Turbo","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.7","name":"Grok 4.7","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":1,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1,"cache_write":4}},"canonical_model_id":"xai/grok-4.7","display_name":"Grok 4.7","type":"chat"},{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"cache_write":1.25,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"cache_write":2.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4,"cache_write":2.5}},"canonical_model_id":"xai/grok-4.3","display_name":"Grok 4.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":0.6,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6,"cache_write":4}},"canonical_model_id":"xai/grok-4.5","display_name":"Grok 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"cache_write":1,"tiers":[{"input":2,"output":4,"cache_read":0.4,"cache_write":2,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4,"cache_write":2}},"canonical_model_id":"xai/grok-build-0.1","display_name":"Grok Build 0.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":1,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1,"cache_write":4}},"canonical_model_id":"xai/grok-4.6","display_name":"Grok 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xiaomi/mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.47,"output":0.94,"cache_read":0.005,"cache_write":0.47},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.16,"output":0.32,"cache_read":0.004,"cache_write":0.16},"canonical_model_id":"xiaomi/mimo-v2.5","display_name":"MiMo-V2.5","type":"chat"},{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.47,"output":0.94,"cache_read":0.005,"cache_write":0.47},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo-V2.5-Pro","type":"chat"},{"id":"xiaomi/mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.16,"output":0.32,"cache_read":0.004,"cache_write":0.16},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.33,"output":1.32,"cache_read":0.066,"cache_write":0.42},"canonical_model_id":"minimax/MiniMax-M2.7","display_name":"MiniMax-M2.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":512000},"cost":{"input":0.33,"output":1.32,"cache_read":0.066,"cache_write":0.33,"tiers":[{"input":0.66,"output":2.63,"cache_read":0.132,"cache_write":0.66,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.66,"output":2.63,"cache_read":0.132,"cache_write":0.66}},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.75},"canonical_model_id":"google/gemini-3.6-flash","display_name":"Gemini 3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3},"canonical_model_id":"google/gemini-3.5-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":4}},"canonical_model_id":"google/gemini-3.1-pro-preview","display_name":"Gemini 3.1 Pro Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":1.5},"canonical_model_id":"google/gemini-3.5-flash","display_name":"Gemini 3.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":1.25,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5}},"canonical_model_id":"google/gemini-2.5-pro","display_name":"Gemini 2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3},"canonical_model_id":"google/gemini-2.5-flash","display_name":"Gemini 2.5 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.75},"canonical_model_id":"google/gemini-3.7-flash","display_name":"Gemini 3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.5},"canonical_model_id":"google/gemini-3-flash-preview","display_name":"Gemini 3 Flash Preview","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-3.8-flash","name":"Gemini 3.8 Flash","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","family":"gemini-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-09-02","last_updated":"2026-09-02","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.75},"canonical_model_id":"google/gemini-3.8-flash","display_name":"Gemini 3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.1},"canonical_model_id":"google/gemini-2.5-flash-lite","display_name":"Gemini 2.5 Flash-Lite","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini/gemini-4-argon","name":"Gemini 4 Argon","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","family":"gemini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2},"canonical_model_id":"google/gemini-4-argon","display_name":"Gemini 4 Argon","type":"chat"},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.88,"output":5.63,"cache_read":0.375,"cache_write":2.35},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.88,"output":5.63,"cache_read":0.23,"cache_write":2.35},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991808,"output":65536},"cost":{"input":0.04,"output":0.13,"cache_read":0.01,"cache_write":0.04,"tiers":[{"input":0.1,"output":0.37,"cache_read":0.02,"cache_write":0.12,"tier":{"type":"context","size":32000}},{"input":0.19,"output":0.74,"cache_read":0.04,"cache_write":0.24,"tier":{"type":"context","size":256000}}]},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.13,"output":0.43,"cache_read":0.016,"cache_write":0.13},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","type":"chat"},{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.19,"output":1.13,"cache_read":0.019,"cache_write":0.24,"tiers":[{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.94,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.94}},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.13,"output":0.43,"cache_read":0.016,"cache_write":0.2},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.32,"output":1.88,"cache_read":0.032,"cache_write":0.4,"tiers":[{"input":1.25,"output":7.5,"cache_read":0.124,"cache_write":1.57,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.25,"output":7.5,"cache_read":0.124,"cache_write":1.57}},"canonical_model_id":"alibaba/qwen3.6-plus","display_name":"Qwen3.6 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.32,"output":1.25,"cache_read":0.032,"cache_write":0.4,"tiers":[{"input":0.96,"output":3.75,"cache_read":0.096,"cache_write":1.2,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.96,"output":3.75,"cache_read":0.096,"cache_write":1.2}},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":5}},"canonical_model_id":"openai/gpt-5.4","display_name":"GPT-5.4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"canonical_model_id":"openai/gpt-5.5-pro","display_name":"GPT-5.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0.2},"canonical_model_id":"openai/gpt-5.4-nano","display_name":"GPT-5.4 nano","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.15},"canonical_model_id":"openai/gpt-4o-mini","display_name":"GPT-4o mini","type":"chat"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75},"canonical_model_id":"openai/gpt-5.4-mini","display_name":"GPT-5.4 mini","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":10}},"canonical_model_id":"openai/gpt-5.5","display_name":"GPT-5.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"},{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":1,"output":4.16,"cache_read":0.18,"cache_write":1},"canonical_model_id":"moonshotai/kimi-k2.6","display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":1,"output":4.16,"cache_read":0.18,"cache_write":1},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"arcee":{"id":"arcee","api":"https://api.arcee.ai/api/v1","name":"Arcee","doc":"https://docs.arcee.ai","display_name":"Arcee","models":[{"id":"trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0.25,"output":0.8,"cache_read":0.06},"canonical_model_id":"arcee-ai/trinity-large-thinking","display_name":"Trinity Large Thinking","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"status":"beta","cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":384000},"status":"beta","cost":{"input":1.74,"output":3.48,"cache_read":0.2},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"status":"beta","cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash Latest","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0.5,"output":1.2,"cache_read":0.1},"canonical_model_id":"thinkingmachines/inkling-small","display_name":"Inkling Small","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"beta","cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"status":"beta","cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}}]},"drun":{"id":"drun","api":"https://chat.d.run/v1","name":"D.Run (China)","doc":"https://www.d.run","display_name":"D.Run (China)","models":[{"id":"public/deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.28,"output":1.1},"display_name":"DeepSeek V3","type":"chat"},{"id":"public/minimax-m25","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.29,"output":1.16},"display_name":"MiniMax M2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"public/deepseek-r1","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32000},"cost":{"input":0.55,"output":2.2},"display_name":"DeepSeek R1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"amd":{"id":"amd","api":"https://developer.amd.com.cn/radeon/api/v1","name":"AMD","doc":"https://developer.amd.com.cn/radeon/tokenfactory","display_name":"AMD","models":[{"id":"Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"DeepSeek-V4-Flash","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"Qwen3.8-Flash-Next","name":"Qwen3.8 Flash Next","description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-27","last_updated":"2026-08-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-flash-next","display_name":"Qwen3.8 Flash Next","type":"chat"},{"id":"MiniCPM5-2B","name":"MiniCPM5-2B","description":"Dense 2B-class open-source model for on-device and resource-constrained use, with native long-context support, tool calling, and agentic tasks","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-09-06","last_updated":"2026-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.124,"output":0.7425,"cache_read":0.124},"canonical_model_id":"openbmb/minicpm5-2b","display_name":"MiniCPM5-2B","type":"chat"},{"id":"DeepSeek-V4-Flash-Vision-Exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}}]},"qvac":{"id":"qvac","name":"QVAC","doc":"https://www.npmjs.com/package/@qvac/ai-sdk-provider","display_name":"QVAC","models":[{"id":"qwen3.5-0.8b","name":"Qwen3.5 0.8B","description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen3.5 0.8B","type":"chat"},{"id":"gemma4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"google/gemma-4-31b-it","display_name":"Gemma 4 31B IT","type":"chat"},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-2b","name":"Qwen3.5 2B","description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen3.5 2B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-oss-20b","display_name":"GPT OSS 20B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.5-9b","display_name":"Qwen3.5 9B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-4b","name":"Qwen3.5 4B","description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true},"tool_call":true,"temperature":true,"release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"display_name":"Qwen3.5 4B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"canonical_model_id":"alibaba/qwen3.6-27b","display_name":"Qwen3.6 27B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"canonical_model_id":"openai/gpt-oss-120b","display_name":"GPT OSS 120B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}}]},"claudinio":{"id":"claudinio","api":"https://api.claudin.io/v1","name":"Claudinio","doc":"https://claudin.io","display_name":"Claudinio","models":[{"id":"claudinio","name":"Claudinio","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"knowledge":"2026-05","release_date":"2026-05-12","last_updated":"2026-06-02","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.5,"output":2,"cache_read":0.15},"display_name":"Claudinio","type":"chat"},{"id":"claudius","name":"Claudius","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"knowledge":"2026-05","release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":3,"output":8,"cache_read":0.9},"display_name":"Claudius","type":"chat"}]},"runinfra":{"id":"runinfra","api":"https://api.runinfra.ai/v1","name":"RunInfra","doc":"https://runinfra.ai/docs","display_name":"RunInfra","models":[{"id":"Inferact/Qwen3.8-2.4T-A95B-NVFP4","name":"Qwen3.8 2.4T A95B (NVFP4)","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.8-2.4t-a95b","display_name":"Qwen3.8 2.4T A95B (NVFP4)","type":"chat"},{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8 27B","type":"chat"},{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.13,"output":0.27,"cache_read":0.01},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.6,"output":1.9,"cache_read":0.03},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/GLM-5.3-Flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true}}},{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.15,"cache_read":0.01},"canonical_model_id":"nvidia/nemotron-3.5-lightning","display_name":"Nemotron 3.5 Lightning 30B A3B","type":"chat"},{"id":"ornith-ai/Ornith-1.5-35B-A3B","name":"Ornith 1.5 35B A3B","description":"Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding","family":"ornith","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-18","last_updated":"2026-08-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"canonical_model_id":"deepreinforce/ornith-1.5-35b-a3b","display_name":"Ornith 1.5 35B A3B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"hetzner":{"id":"hetzner","api":"https://inference.hetzner.com/api/v1","name":"Hetzner","doc":"https://experiments.hetzner.com/docs/inference","display_name":"Hetzner","models":[{"id":"Qwen3.8-27B","name":"Qwen3.8-27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"alibaba/qwen3.8-27b","display_name":"Qwen3.8-27B","type":"chat"},{"id":"Qwen/Qwen3.6-35B-A3B-FP8","name":"Qwen3.6 35B A3B FP8","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0,"output":0,"cache_read":0},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B A3B FP8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}}]},"digitalocean":{"id":"digitalocean","api":"https://inference.do-ai.run/v1","name":"DigitalOcean","doc":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","display_name":"DigitalOcean","models":[{"id":"deepseek-3.2","name":"Deepseek 3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2025-12-02","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.5,"output":1.6,"cache_read":0.15},"display_name":"Deepseek 3.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"openai-gpt-5.5","name":"OpenAI GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"display_name":"OpenAI GPT-5.5","type":"chat"},{"id":"openai-gpt-5.2-pro","name":"OpenAI GPT-5.2 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":21,"output":168},"display_name":"OpenAI GPT-5.2 Pro","type":"chat"},{"id":"all-mini-lm-l6-v2","name":"All-MiniLM-L6-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2021-08-30","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256,"output":384},"cost":{"input":0.009,"output":0},"display_name":"All-MiniLM-L6-v2","type":"chat"},{"id":"multi-qa-mpnet-base-dot-v1","name":"Multi-QA-mpnet-base-dot-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2021-08-30","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":768},"cost":{"input":0.009,"output":0},"display_name":"Multi-QA-mpnet-base-dot-v1","type":"chat"},{"id":"openai-gpt-image-1","name":"GPT Image 1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":5,"output":40,"cache_read":1.25},"display_name":"GPT Image 1","type":"chat"},{"id":"anthropic-claude-3-opus","name":"Claude 3 Opus","description":"Legacy model retained for compatibility with older integrations","family":"claude-opus","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-08","release_date":"2024-02-29","last_updated":"2024-02-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Claude 3 Opus","type":"chat"},{"id":"anthropic-claude-4.6-sonnet","name":"Anthropic Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"display_name":"Anthropic Claude Sonnet 4.6","type":"chat"},{"id":"anthropic-claude-haiku-4.5","name":"Anthropic Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"display_name":"Anthropic Claude Haiku 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"glm-5.3-flash","name":"GLM5.3 Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM5.3 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai-o1","name":"OpenAI o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"display_name":"OpenAI o1","type":"chat"},{"id":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic-claude-opus-4.7","name":"Anthropic Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Anthropic Claude Opus 4.7","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"stable-diffusion-3.5-large","name":"Stable Diffusion 3.5 Large","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-10-22","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":256,"output":1},"cost":{"input":0.08,"output":0},"display_name":"Stable Diffusion 3.5 Large","type":"chat"},{"id":"openai-gpt-6-luna","name":"OpenAI GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02}},"canonical_model_id":"openai/gpt-6-luna","display_name":"OpenAI GPT-6 Luna","type":"chat"},{"id":"qwen3.8-max","name":"Qwen3.8-Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":262144},"cost":{"input":2,"output":6,"cache_read":0.2},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8-Max","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"anthropic-claude-opus-5.5","name":"Anthropic Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.4,"cache_write":10,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.4,"cache_write":10}},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Anthropic Claude Opus 5.5","type":"chat"},{"id":"openai-gpt-6-1-sol","name":"OpenAI GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.1,"tiers":[{"input":4,"output":15,"cache_read":0.2,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"OpenAI GPT-6.1 Sol","type":"chat"},{"id":"llama-4-maverick","name":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.25,"output":0.87,"cache_read":0.05},"display_name":"Llama 4 Maverick","type":"chat"},{"id":"openai-o3-mini","name":"OpenAI o3 mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"display_name":"OpenAI o3 mini","type":"chat"},{"id":"glm-5","name":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":64000},"cost":{"input":1,"output":3.2,"cache_read":0.2},"display_name":"GLM 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2.5","name":"MiniMax M2.5 (Public Preview)","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-m2.5","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2026-02-12","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"MiniMax M2.5 (Public Preview)","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic-claude-4.1-opus","name":"Anthropic Claude 4.1 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Anthropic Claude 4.1 Opus","type":"chat"},{"id":"anthropic-claude-sonnet-5.5","name":"Anthropic Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Anthropic Claude Sonnet 5.5","type":"chat"},{"id":"wan2-2-t2v-a14b","name":"Wan2.2-T2V-A14B","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-07-28","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["video"]},"open_weights":true,"limit":{"context":100,"output":1},"cost":{"input":0.6,"output":0},"display_name":"Wan2.2-T2V-A14B","type":"chat"},{"id":"openai-gpt-4o","name":"OpenAI GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"display_name":"OpenAI GPT-4o","type":"chat"},{"id":"anthropic-claude-fable-5.1","name":"Anthropic Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Anthropic Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"display_name":"Kimi K2.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"nemotron-3.5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.3,"output":0.65,"cache_read":0.06},"display_name":"NVIDIA Nemotron 3.5 Super VL","type":"chat"},{"id":"deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-12-26","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":131072},"display_name":"DeepSeek V3","type":"chat"},{"id":"deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32678,"output":8192},"cost":{"input":0.99,"output":0.99},"display_name":"DeepSeek R1 Distill Llama 70B","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai-gpt-5-nano","name":"OpenAI GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"display_name":"OpenAI GPT-5 Nano","type":"chat"},{"id":"qwen3-embedding-0.6b","name":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-06-03","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":1024},"status":"beta","cost":{"input":0.04,"output":0},"display_name":"Qwen3 Embedding 0.6B","type":"embedding"},{"id":"mistral-7b-instruct-v0.3","name":"Mistral 7B Instruct v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-05-22","last_updated":"2024-05-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"display_name":"Mistral 7B Instruct v0.3","type":"chat"},{"id":"anthropic-claude-5.5-haiku","name":"Anthropic Claude 5.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Anthropic Claude 5.5 Haiku","type":"chat"},{"id":"qwen-2.5-14b-instruct","name":"Qwen 2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"display_name":"Qwen 2.5 14B Instruct","type":"chat"},{"id":"openai-o3","name":"OpenAI o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"OpenAI o3","type":"chat"},{"id":"openai-gpt-5","name":"OpenAI GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"OpenAI GPT-5","type":"chat"},{"id":"openai-gpt-4.1","name":"OpenAI GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"display_name":"OpenAI GPT-4.1","type":"chat"},{"id":"openai-gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"display_name":"GPT-5.1 Codex Max","type":"chat"},{"id":"anthropic-claude-3.5-haiku","name":"Claude 3.5 Haiku","description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-11-05","last_updated":"2024-11-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","cost":{"input":0.8,"output":4,"cache_read":0.08,"cache_write":1},"display_name":"Claude 3.5 Haiku","type":"chat"},{"id":"anthropic-claude-3.5-sonnet","name":"Claude 3.5 Sonnet","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-06-20","last_updated":"2024-10-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude 3.5 Sonnet","type":"chat"},{"id":"kimi-k2.5","name":"Kimi K2.5","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.7,"cache_read":0.203},"display_name":"Kimi K2.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"anthropic-claude-opus-4","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"display_name":"Claude Opus 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"openai-gpt-6-astra","name":"OpenAI GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"tiers":[{"input":20,"output":75,"cache_read":2,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2}},"canonical_model_id":"openai/gpt-6-astra","display_name":"OpenAI GPT-6 Astra","type":"chat"},{"id":"openai-gpt-image-2","name":"OpenAI GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image","text"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":8,"output":30},"display_name":"OpenAI GPT Image 2","type":"chat"},{"id":"openai-gpt-image-1.5","name":"OpenAI GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["image","text"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":5,"output":10,"cache_read":1},"display_name":"OpenAI GPT Image 1.5","type":"chat"},{"id":"openai-gpt-4o-mini","name":"OpenAI GPT-4o mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"display_name":"OpenAI GPT-4o mini","type":"chat"},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":1.7,"cache_read":0.09},"display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"deepseek-4-flash","name":"Deepseek V4 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-05-27","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"display_name":"Deepseek V4 Flash","type":"chat"},{"id":"nemotron-3-ultra-550b","name":"Nemotron 3 Ultra","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.9,"output":1.7,"cache_read":0.18},"display_name":"Nemotron 3 Ultra","type":"chat"},{"id":"openai-gpt-5.2","name":"OpenAI GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"OpenAI GPT-5.2","type":"chat"},{"id":"nvidia-nemotron-3-super-120b","name":"NVIDIA Nemotron 3 Super 120B  (Public Preview)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.3,"output":0.65,"cache_read":0.06},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"NVIDIA Nemotron 3 Super 120B  (Public Preview)","type":"chat"},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.8,"output":3,"cache_read":0.16},"canonical_model_id":"xiaomi/mimo-v2.5-pro","display_name":"MiMo V2.5 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mistral-3-14B","name":"Ministral 3 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.2,"output":0.2,"cache_read":0.04},"display_name":"Ministral 3 14B","type":"chat"},{"id":"anthropic-claude-opus-5","name":"Anthropic Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Anthropic Claude Opus 5","type":"chat"},{"id":"nemotron-3-nano-omni","name":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":0.9,"cache_read":0.1},"canonical_model_id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","display_name":"Nemotron 3 Nano Omni","type":"chat"},{"id":"nemotron-3-nano-30b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","type":"chat"},{"id":"arcee-trinity-large-thinking","name":"Arcee Trinity Large Thinking (Public Preview)","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.25,"output":0.9,"cache_read":0.06},"canonical_model_id":"arcee-ai/trinity-large-thinking","display_name":"Arcee Trinity Large Thinking (Public Preview)","type":"chat"},{"id":"anthropic-claude-5-sonnet","name":"Anthropic Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5","display_name":"Anthropic Claude Sonnet 5","type":"chat"},{"id":"openai-gpt-5.4-pro","name":"OpenAI GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"display_name":"OpenAI GPT-5.4 Pro","type":"chat"},{"id":"llama3-8b-instruct","name":"Llama 3.1 Instruct (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.198,"output":0.198},"display_name":"Llama 3.1 Instruct (8B)","type":"chat"},{"id":"llama3.3-70b-instruct","name":"Llama 3.3 Instruct (70B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.65,"output":0.65},"display_name":"Llama 3.3 Instruct (70B)","type":"chat"},{"id":"openai-gpt-oss-120b","name":"OpenAI GPT-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-05","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.1,"output":0.7,"cache_read":0.02},"display_name":"OpenAI GPT-oss-120b","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alibaba-qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.25,"output":0.55},"display_name":"Qwen3 32B","type":"chat"},{"id":"openai-gpt-5.3-codex","name":"OpenAI GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"display_name":"OpenAI GPT-5.3 Codex","type":"chat"},{"id":"qwen3.5-397b-a17b","name":"Qwen 3.5 397B A17B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen3.5","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-04-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.55,"output":3.5,"cache_read":0.111},"display_name":"Qwen 3.5 397B A17B","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"anthropic-claude-3.7-sonnet","name":"Claude 3.7 Sonnet","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-02-24","last_updated":"2025-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"display_name":"Claude 3.7 Sonnet","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"anthropic-claude-opus-4.8","name":"Anthropic Claude Opus 4.8","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-28","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Anthropic Claude Opus 4.8","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"openai-gpt-5.6-luna","name":"OpenAI GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"OpenAI GPT-5.6 Luna","type":"chat"},{"id":"qwen3-tts-voicedesign","name":"Qwen3 TTS VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":32768,"output":1},"display_name":"Qwen3 TTS VoiceDesign","type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.21},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai-gpt-6-sol","name":"OpenAI GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"tiers":[{"input":4,"output":15,"cache_read":0.4,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4}},"canonical_model_id":"openai/gpt-6-sol","display_name":"OpenAI GPT-6 Sol","type":"chat"},{"id":"anthropic-claude-4.5-sonnet","name":"Anthropic Claude 4.5 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"display_name":"Anthropic Claude 4.5 Sonnet","type":"chat"},{"id":"bge-m3","name":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bge","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-01-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1024},"cost":{"input":0.02,"output":0},"display_name":"BGE M3","type":"embedding"},{"id":"ministral-3-8b-instruct-2512","name":"Ministral 3 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"display_name":"Ministral 3 8B","type":"chat"},{"id":"openai-gpt-5.6-sol","name":"OpenAI GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"tiers":[{"input":8,"output":30,"cache_read":0.8,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"OpenAI GPT-5.6 Sol","type":"chat"},{"id":"glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":1.3,"output":4.3,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.1","display_name":"GLM-5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"openai-gpt-5.4-nano","name":"OpenAI GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"display_name":"OpenAI GPT-5.4 Nano","type":"chat"},{"id":"bge-reranker-v2-m3","name":"BGE Reranker v2 M3","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"bge","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-03-12","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1},"cost":{"input":0.01,"output":0},"display_name":"BGE Reranker v2 M3","type":"rerank"},{"id":"nemotron-nano-12b-v2-vl","name":"Nemotron-nano 12b v2-vl","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.2,"output":0.6,"cache_read":0.04},"canonical_model_id":"nvidia/nemotron-nano-12b-v2-vl","display_name":"Nemotron-nano 12b v2-vl","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai-gpt-5.4-mini","name":"OpenAI GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"display_name":"OpenAI GPT-5.4 Mini","type":"chat"},{"id":"openai-gpt-5-mini","name":"OpenAI GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"display_name":"OpenAI GPT-5 Mini","type":"chat"},{"id":"anthropic-claude-opus-4.6","name":"Anthropic Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"display_name":"Anthropic Claude Opus 4.6","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"e5-large-v2","name":"E5 Large v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-05-19","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.02,"output":0},"display_name":"E5 Large v2","type":"chat"},{"id":"anthropic-claude-opus-4.5","name":"Anthropic Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"display_name":"Anthropic Claude Opus 4.5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"deepseek-v4-pro","name":"Deepseek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.348},"display_name":"Deepseek V4 Pro","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"gemma-4-31B-it","name":"Gemma 4","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.18,"output":0.5,"cache_read":0.036},"display_name":"Gemma 4","type":"chat"},{"id":"openai-gpt-5.6-terra","name":"OpenAI GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"OpenAI GPT-5.6 Terra","type":"chat"},{"id":"glm-5.3","name":"GLM5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gte-large-en-v1.5","name":"GTE Large (v1.5)","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-03-27","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1024},"cost":{"input":0.09,"output":0},"display_name":"GTE Large (v1.5)","type":"chat"},{"id":"anthropic-claude-fable-5","name":"Anthropic Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-06-09","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"display_name":"Anthropic Claude Fable 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"openai-gpt-oss-20b","name":"OpenAI GPT-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-05","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.05,"output":0.45,"cache_read":0.01},"display_name":"OpenAI GPT-oss-20b","type":"chat"},{"id":"openai-gpt-5.4","name":"OpenAI GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"display_name":"OpenAI GPT-5.4","type":"chat"},{"id":"mistral-nemo-instruct-2407","name":"Mistral Nemo Instruct","description":"Legacy model retained for compatibility with older integrations","family":"mistral","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":0.3,"output":0.3},"display_name":"Mistral Nemo Instruct","type":"chat"},{"id":"anthropic-claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75}},"display_name":"Claude Sonnet 4","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"fal-ai/fast-sdxl","name":"Fast SDXL","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-07-26","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":8192,"output":8192},"display_name":"Fast SDXL","type":"chat"},{"id":"fal-ai/elevenlabs/tts/multilingual-v2","name":"ElevenLabs Multilingual TTS v2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2023-08-22","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"ElevenLabs Multilingual TTS v2","type":"chat"},{"id":"fal-ai/flux/schnell","name":"FLUX.1 [schnell]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2024-08-01","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":8192,"output":8192},"display_name":"FLUX.1 [schnell]","type":"chat"},{"id":"fal-ai/stable-audio-25/text-to-audio","name":"Stable Audio 2.5 (Text-to-Audio)","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"release_date":"2025-10-08","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":8192},"display_name":"Stable Audio 2.5 (Text-to-Audio)","type":"chat"}]},"boundless":{"id":"boundless","api":"https://api.inference.boundless.network/v1","name":"Boundless","doc":"https://inference.boundless.network/models","display_name":"Boundless","models":[{"id":"nemotron3-super","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.12,"output":0.52,"cache_read":0.06},"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","type":"chat"},{"id":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"canonical_model_id":"xiaomi/mimo-v2.6-pro","display_name":"MiMo-V2.6-Pro","type":"chat"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.12,"output":0.4,"cache_read":0.024},"canonical_model_id":"zhipuai/glm-5.3-flash","display_name":"GLM-5.3-Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2.3,"output":11.4,"cache_read":0.23},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.2,"output":1,"cache_read":0.01},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"canonical_model_id":"anthropic/claude-opus-5","display_name":"Claude Opus 5","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.6","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.04,"output":0.35,"cache_read":0.02},"canonical_model_id":"alibaba/qwen3.6-35b-a3b","display_name":"Qwen3.6 35B-A3B","type":"chat"},{"id":"claude-fable-5.1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":128000},"cost":{"input":10,"output":50,"cache_read":0.25},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.04,"output":2.08,"cache_read":0.0352},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","description":"MiMo Flash model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"xiaomi/mimo-v2.6-flash","display_name":"MiMo-V2.6-Flash","type":"chat"},{"id":"minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.28,"output":1.1,"cache_read":0.056},"canonical_model_id":"minimax/MiniMax-M3","display_name":"MiniMax-M3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"dsv4","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.04,"output":0.21,"cache_read":0.02},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.34,"output":2.3,"cache_read":0.17},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1,"output":0.5,"cache_read":0.01},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"claude-opus-5.5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.2},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.12,"output":3.52,"cache_read":0.14},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"aixy":{"id":"aixy","api":"https://api.aixy-gateway.com/v1","name":"Aixy","doc":"https://docs.aixy-gateway.com/integrations/overview","display_name":"Aixy","models":[{"id":"anthropic/claude-opus-5-5","name":"Claude Opus 5.5","description":"Claude model for long-running agentic coding and knowledge work","family":"claude-opus","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.aixy-gateway.com/v1"},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"canonical_model_id":"anthropic/claude-opus-5-5","display_name":"Claude Opus 5.5","type":"chat"},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1","description":"Claude model for demanding reasoning and long-horizon agentic work","family":"claude-fable","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.aixy-gateway.com/v1"},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"canonical_model_id":"anthropic/claude-fable-5-1","display_name":"Claude Fable 5.1","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-haiku-5-5","name":"Claude Haiku 5.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.aixy-gateway.com/v1"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625,"tier":{"type":"context","size":100000}}]},"canonical_model_id":"anthropic/claude-haiku-5-5","display_name":"Claude Haiku 5.5","type":"chat"},{"id":"anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5","description":"Fast Claude model for everyday coding, agents, and knowledge work","family":"claude-sonnet","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.aixy-gateway.com/v1"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"canonical_model_id":"anthropic/claude-sonnet-5-5","display_name":"Claude Sonnet 5.5","type":"chat"},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.aixy-gateway.com/v1","shape":"responses"},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.2,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.2,"cache_write":5}},"canonical_model_id":"openai/gpt-6.1-sol","display_name":"GPT-6.1 Sol","type":"chat"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","family":"gpt-astra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.aixy-gateway.com/v1","shape":"responses"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"tiers":[{"input":20,"output":75,"cache_read":2,"cache_write":25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":20,"output":75,"cache_read":2,"cache_write":25}},"canonical_model_id":"openai/gpt-6-astra","display_name":"GPT-6 Astra","type":"chat","extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.aixy-gateway.com/v1","shape":"responses"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"canonical_model_id":"openai/gpt-5.6-luna","display_name":"GPT-5.6 Luna","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","description":"OpenAI's most efficient model for focused, high-volume tasks","family":"gpt-luna","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.aixy-gateway.com/v1","shape":"responses"},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"tiers":[{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}},"canonical_model_id":"openai/gpt-6-luna","display_name":"GPT-6 Luna","type":"chat"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.aixy-gateway.com/v1","shape":"responses"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-5.6-terra","display_name":"GPT-5.6 Terra","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.aixy-gateway.com/v1","shape":"responses"},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"canonical_model_id":"openai/gpt-5.6-sol","display_name":"GPT-5.6 Sol","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","description":"OpenAI model for complex coding and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.aixy-gateway.com/v1","shape":"responses"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"canonical_model_id":"openai/gpt-6-sol","display_name":"GPT-6 Sol","type":"chat"}]},"alibaba-cn":{"id":"alibaba-cn","api":"https://dashscope.aliyuncs.com/compatible-mode/v1","name":"alibaba-cn","doc":"https://www.alibabacloud.com/help/en/model-studio/models","display_name":"alibaba-cn","models":[{"id":"qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.022,"output":0.216},"display_name":"Qwen Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-23","last_updated":"2026-09-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.029,"output":0.287,"reasoning":0.287,"tiers":[{"input":0.115,"output":1.147,"reasoning":1.147,"tier":{"type":"context","size":128000}},{"input":0.172,"output":1.72,"reasoning":1.72,"tier":{"type":"context","size":256000}}]},"display_name":"Qwen3.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen2-5-coder-32b-instruct","name":"Qwen2.5-Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11","last_updated":"2024-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.861},"display_name":"Qwen2.5-Coder 32B Instruct","type":"chat"},{"id":"deepseek-v3-2-exp","name":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.287,"output":0.431},"display_name":"DeepSeek V3.2 Exp","type":"chat"},{"id":"deepseek-r1-distill-qwen-14b","name":"DeepSeek R1 Distill Qwen 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.144,"output":0.431},"display_name":"DeepSeek R1 Distill Qwen 14B","type":"chat"},{"id":"qwen-math-plus","name":"Qwen Math Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-08-16","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":3072},"cost":{"input":0.574,"output":1.721},"display_name":"Qwen Math Plus","type":"chat"},{"id":"qwen-deep-research","name":"Qwen Deep Research","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":7.742,"output":23.367},"display_name":"Qwen Deep Research","type":"chat"},{"id":"qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"canonical_model_id":"alibaba/qwen3.7-max","display_name":"Qwen3.7 Max","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"qwen2-5-32b-instruct","name":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.861},"display_name":"Qwen2.5 32B Instruct","type":"chat"},{"id":"qwq-plus","name":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":32768,"default":32768}},"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.23,"output":0.574},"display_name":"QwQ Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwq-32b","name":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.861},"display_name":"QwQ 32B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.294,"output":6.881},"display_name":"Qwen2.5-VL 72B Instruct","type":"chat"},{"id":"deepseek-v3-1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.574,"output":1.721},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"qwen3-vl-plus","name":"Qwen3 VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.143353,"output":1.433525,"reasoning":4.300576},"display_name":"Qwen3 VL Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus-character","name":"Qwen Plus Character","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.115,"output":0.287},"display_name":"Qwen Plus Character","type":"chat"},{"id":"qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.345,"output":1.377},"display_name":"Qwen Max","search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.144,"output":1.434},"display_name":"Qwen3 Next 80B A3B Thinking","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"],"exclusive_with":["budget_tokens"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.77744,"output":5.33231,"cache_read":0.22218,"cache_write":2.22179},"canonical_model_id":"alibaba/qwen3.8-max","display_name":"Qwen3.8 Max","extra_capabilities":{"reasoning":{"supported":true,"budget":{"min":0,"max":262144,"unit":"tokens"},"effort_options":["none","low","medium","xhigh"],"continuation":["thinking_blocks"],"notes":["Prefer reasoning_effort; thinking_budget is an alternative, not an additional control.","Omitting both controls differs from explicitly selecting xhigh, which maps to 262144 budget tokens."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"xhigh"}},"type":"chat"},{"id":"kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":2.827,"output":14.133,"cache_read":0.283},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen2-5-math-7b-instruct","name":"Qwen2.5-Math 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":3072},"cost":{"input":0.144,"output":0.287},"display_name":"Qwen2.5-Math 7B Instruct","type":"chat"},{"id":"qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-09-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.115,"output":0.688,"reasoning":0.688,"tiers":[{"input":0.287,"output":1.72,"reasoning":1.72,"tier":{"type":"context","size":128000}},{"input":0.573,"output":3.44,"reasoning":3.44,"tier":{"type":"context","size":256000}}]},"display_name":"Qwen3.5 Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen2-5-72b-instruct","name":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.574,"output":1.721},"display_name":"Qwen2.5 72B Instruct","type":"chat"},{"id":"glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0.573,"output":2.58,"tiers":[{"input":0.86,"output":3.154,"tier":{"type":"context","size":32000}}]},"display_name":"GLM-5","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.29754,"output":1.19015,"cache_read":0.01488},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"deepseek-r1-distill-llama-8b","name":"DeepSeek R1 Distill Llama 8B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"display_name":"DeepSeek R1 Distill Llama 8B","type":"chat"},{"id":"qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.287,"output":1.147,"reasoning":2.868},"display_name":"Qwen3 32B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen2-5-coder-7b-instruct","name":"Qwen2.5-Coder 7B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11","last_updated":"2024-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.144,"output":0.287},"display_name":"Qwen2.5-Coder 7B Instruct","type":"chat"},{"id":"qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.115,"output":0.287,"reasoning":1.147,"cache_read":0.012,"cache_write":0.144},"display_name":"Qwen Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991808,"output":131072},"cost":{"input":0.02962,"output":0.1185,"cache_read":0.002962,"cache_write":0.03703,"tiers":[{"input":0.08887,"output":0.35549,"cache_read":0.008887,"cache_write":0.11109,"tier":{"type":"context","size":32000}},{"input":0.17774,"output":0.71098,"cache_read":0.017774,"cache_write":0.22218,"tier":{"type":"context","size":256000}}]},"canonical_model_id":"alibaba/qwen3.7-flash","display_name":"Qwen3.7 Flash","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"kimi-k2.6","name":"Moonshot Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.929,"output":3.858},"display_name":"Moonshot Kimi K2.6","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-23","last_updated":"2026-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.359,"output":1.434,"reasoning":1.434,"tiers":[{"input":0.574,"output":2.294,"reasoning":2.294,"tier":{"type":"context","size":32000}},{"input":1.004,"output":4.014,"reasoning":4.014,"tier":{"type":"context","size":128000}}]},"display_name":"Qwen3 Max","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-omni-turbo-realtime","name":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-05-08","last_updated":"2025-05-08","modalities":{"input":["text","image","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.23,"output":0.918,"input_audio":3.584,"output_audio":7.168},"display_name":"Qwen-Omni Turbo Realtime","type":"chat"},{"id":"deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0.287,"output":1.147},"display_name":"DeepSeek V3","type":"chat"},{"id":"deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.287,"output":0.861},"display_name":"DeepSeek R1 Distill Llama 70B","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.861,"output":3.441,"tiers":[{"input":1.291,"output":5.161,"tier":{"type":"context","size":32000}},{"input":2.151,"output":8.602,"tier":{"type":"context","size":128000}}]},"display_name":"Qwen3-Coder 480B-A35B Instruct","type":"chat"},{"id":"qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.044,"output":0.087,"reasoning":0.431},"display_name":"Qwen Turbo","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"deepseek-r1-distill-qwen-7b","name":"DeepSeek R1 Distill Qwen 7B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.072,"output":0.144},"display_name":"DeepSeek R1 Distill Qwen 7B","type":"chat"},{"id":"qwen2-5-math-72b-instruct","name":"Qwen2.5-Math 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":3072},"cost":{"input":0.574,"output":1.721},"display_name":"Qwen2.5-Math 72B Instruct","type":"chat"},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.216,"output":0.861,"tiers":[{"input":0.323,"output":1.291,"tier":{"type":"context","size":32000}},{"input":0.538,"output":2.151,"tier":{"type":"context","size":128000}}]},"display_name":"Qwen3-Coder 30B-A3B Instruct","type":"chat"},{"id":"qwen-doc-turbo","name":"Qwen Doc Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.087,"output":0.144},"display_name":"Qwen Doc Turbo","type":"chat"},{"id":"kimi-k2-thinking","name":"Moonshot Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.574,"output":2.294},"display_name":"Moonshot Kimi K2 Thinking","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-09-17","last_updated":"2026-09-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.113,"output":0.382,"cache_read":0.014},"canonical_model_id":"alibaba/qwen3.8-omni-flash","display_name":"Qwen3.8 Omni Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["none","low","medium","xhigh"],"default_enabled":true,"mode":"effort","effort":"xhigh"}},"type":"chat"},{"id":"qvq-max","name":"QVQ Max","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qvq","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":1.147,"output":4.588},"display_name":"QVQ Max","type":"chat"},{"id":"qwen2-5-7b-instruct","name":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.072,"output":0.144},"display_name":"Qwen2.5 7B Instruct","type":"chat"},{"id":"qwen3-omni-flash","name":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.058,"output":0.23,"input_audio":3.584,"output_audio":7.168},"display_name":"Qwen3-Omni Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.23,"output":0.574},"display_name":"Qwen-VL Max","type":"chat"},{"id":"qwen3-235b-a22b","name":"Qwen3 235B A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.287,"output":1.147,"reasoning":2.868},"display_name":"Qwen3 235B A22B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-vl-30b-a3b","name":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.108,"output":0.431,"reasoning":1.076},"display_name":"Qwen3-VL 30B-A3B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"kimi-k2.5","name":"Moonshot Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.574,"output":2.411},"display_name":"Moonshot Kimi K2.5","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.144,"output":0.574},"display_name":"Qwen3 Next 80B A3B Instruct","type":"chat"},{"id":"qwen-vl-plus","name":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.115,"output":0.287},"display_name":"Qwen-VL Plus","type":"chat"},{"id":"deepseek-r1-distill-qwen-1-5b","name":"DeepSeek R1 Distill Qwen 1.5B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"display_name":"DeepSeek R1 Distill Qwen 1.5B","type":"chat"},{"id":"qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"canonical_model_id":"alibaba/qwen3.6-flash","display_name":"Qwen3.6 Flash","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.144,"output":0.574},"display_name":"Qwen3 Coder Flash","type":"chat"},{"id":"qwen2-5-omni-7b","name":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0.087,"output":0.345,"input_audio":5.448},"display_name":"Qwen2.5-Omni 7B","type":"chat"},{"id":"qwen-mt-plus","name":"Qwen Mt Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":0.259,"output":0.775},"display_name":"Qwen Mt Plus","type":"chat"},{"id":"tongyi-intent-detect-v3","name":"Tongyi Intent Detect V3","description":"General-purpose chat model for instruction following, writing, and analysis","family":"yi","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1024},"cost":{"input":0.058,"output":0.144},"display_name":"Tongyi Intent Detect V3","type":"chat"},{"id":"qwen3-vl-235b-a22b","name":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.286705,"output":1.14682,"reasoning":2.867051},"display_name":"Qwen3-VL 235B-A22B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2026-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0.574,"output":2.296,"tiers":[{"input":0.861,"output":3.444,"tier":{"type":"context","size":32000}},{"input":1.435,"output":5.74,"tier":{"type":"context","size":128000}},{"input":2.87,"output":28.7,"tier":{"type":"context","size":256000}}]},"display_name":"Qwen3 Coder Plus","type":"chat"},{"id":"moonshot-kimi-k2-instruct","name":"Moonshot Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.574,"output":2.294},"display_name":"Moonshot Kimi K2 Instruct","type":"chat"},{"id":"MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"display_name":"MiniMax-M2.5","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen2-5-14b-instruct","name":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.144,"output":0.431},"display_name":"Qwen2.5 14B Instruct","type":"chat"},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"],"exclusive_with":["budget_tokens"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2026-08-26","last_updated":"2026-08-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.11875,"output":0.40073,"cache_read":0.01187,"cache_write":0.14844},"canonical_model_id":"alibaba/qwen3.8-flash","display_name":"Qwen3.8 Flash","extra_capabilities":{"reasoning":{"supported":true,"budget":{"min":0,"max":262144,"unit":"tokens"},"effort_options":["none","low","medium","xhigh"],"continuation":["thinking_blocks"],"notes":["Prefer reasoning_effort; thinking_budget is an alternative, not an additional control.","Omitting both controls differs from explicitly selecting xhigh, which maps to 262144 budget tokens."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"xhigh"}},"type":"chat"},{"id":"qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.717},"display_name":"Qwen2.5-VL 7B Instruct","type":"chat"},{"id":"qwen-math-turbo","name":"Qwen Math Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":3072},"cost":{"input":0.287,"output":0.861},"display_name":"Qwen Math Turbo","type":"chat"},{"id":"qwen-long","name":"Qwen Long","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-25","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":8192},"cost":{"input":0.072,"output":0.287},"display_name":"Qwen Long","type":"chat"},{"id":"qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":245800,"output":65536},"cost":{"input":1.32,"output":7.9,"cache_read":0.132},"display_name":"Qwen3.6 Max Preview","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-mt-turbo","name":"Qwen Mt Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":0.101,"output":0.28},"display_name":"Qwen Mt Turbo","type":"chat"},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.172,"output":1.032,"reasoning":1.032,"tiers":[{"input":0.43,"output":2.58,"reasoning":2.58,"tier":{"type":"context","size":128000}}]},"display_name":"Qwen3.5 397B-A17B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-8b","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.072,"output":0.287,"reasoning":0.717},"display_name":"Qwen3 8B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.1,"output":3.851,"cache_read":0.275,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen-omni-turbo","name":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-19","last_updated":"2025-03-26","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.058,"output":0.23,"input_audio":3.584,"output_audio":7.168},"display_name":"Qwen-Omni Turbo","type":"chat"},{"id":"glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0.825,"output":3.301,"cache_read":0.17,"tiers":[{"input":1.1,"output":3.851,"tier":{"type":"context","size":32000}}]},"display_name":"GLM-5.1","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen3-omni-flash-realtime","name":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.23,"output":0.918,"input_audio":3.584,"output_audio":7.168},"display_name":"Qwen3-Omni Flash Realtime","type":"chat"},{"id":"qwen3-asr-flash","name":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":false,"knowledge":"2024-04","release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":53248,"output":4096},"cost":{"input":0.032,"output":0.032},"display_name":"Qwen3-ASR Flash","type":"chat"},{"id":"deepseek-r1-distill-qwen-32b","name":"DeepSeek R1 Distill Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.287,"output":0.861},"display_name":"DeepSeek R1 Distill Qwen 32B","type":"chat"},{"id":"deepseek-r1","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.574,"output":2.294},"display_name":"DeepSeek R1","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"canonical_model_id":"deepseek/deepseek-v4-pro","display_name":"DeepSeek V4 Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"},{"id":"deepseek-r1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.574,"output":2.294},"display_name":"DeepSeek R1 0528","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"display_name":"Qwen3.6 Plus","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-14b","name":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.144,"output":0.574,"reasoning":1.434},"display_name":"Qwen3 14B","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.1,"output":3.851,"cache_read":0.275,"cache_write":0},"canonical_model_id":"zhipuai/glm-5.3","display_name":"GLM-5.3","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":128000}}]},"canonical_model_id":"alibaba/qwen3.7-plus","display_name":"Qwen3.7 Plus","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"canonical_model_id":"deepseek/deepseek-v4-flash","display_name":"DeepSeek V4 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"},{"id":"qwen-vl-ocr","name":"Qwen Vl Ocr","description":"OCR model for extracting structured text from documents and screenshots","family":"qwen","attachment":false,"reasoning":{"supported":false},"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-10-28","last_updated":"2026-09-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":34096,"output":4096},"cost":{"input":0.043,"output":0.072},"display_name":"Qwen Vl Ocr","type":"chat"},{"id":"siliconflow/deepseek-v3-0324","name":"siliconflow/deepseek-v3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":false},"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":163840},"cost":{"input":0.25,"output":1},"display_name":"siliconflow/deepseek-v3-0324","type":"chat"},{"id":"siliconflow/deepseek-v3.1-terminus","name":"siliconflow/deepseek-v3.1-terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":1},"display_name":"siliconflow/deepseek-v3.1-terminus","type":"chat"},{"id":"siliconflow/deepseek-r1-0528","name":"siliconflow/deepseek-r1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":32768},"cost":{"input":0.5,"output":2.18},"display_name":"siliconflow/deepseek-r1-0528","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"siliconflow/deepseek-v3.2","name":"siliconflow/deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":0.42},"display_name":"siliconflow/deepseek-v3.2","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"kimi/kimi-k2.5","name":"kimi/kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"display_name":"kimi/kimi-k2.5","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"MiniMax/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"display_name":"MiniMax-M2.7","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-coder-plus-2025-09-23","name":"Qwen3 Coder Plus 2025 09 23","display_name":"Qwen3 Coder Plus 2025 09 23","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":65536},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen3-coder-plus-2025-07-22","name":"Qwen3 Coder Plus 2025 07 22","display_name":"Qwen3 Coder Plus 2025 07 22","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":65536},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-vl-ocr-latest","name":"Qwen Vl Ocr Latest","display_name":"Qwen Vl Ocr Latest","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":34096,"output":4096},"reasoning":{"supported":false},"type":"chat"},{"id":"qvq-max-2025-05-15","name":"Qvq Max 2025 05 15","display_name":"Qvq Max 2025 05 15","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":16384,"default":16384}},"type":"chat"},{"id":"qwen-turbo-latest","name":"Qwen Turbo Latest","display_name":"Qwen Turbo Latest","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":38912,"default":38912}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-turbo-2024-09-19","name":"Qwen Turbo 2024 09 19","display_name":"Qwen Turbo 2024 09 19","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-flash-2025-07-28","name":"Qwen Flash 2025 07 28","display_name":"Qwen Flash 2025 07 28","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus-latest","name":"Qwen Plus Latest","display_name":"Qwen Plus Latest","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus-2024-09-19","name":"Qwen Plus 2024 09 19","display_name":"Qwen Plus 2024 09 19","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-plus-2025-07-14","name":"Qwen Plus 2025 07 14","display_name":"Qwen Plus 2025 07 14","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":38912,"default":38912}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-plus-2025-09-11","name":"Qwen Plus 2025 09 11","display_name":"Qwen Plus 2025 09 11","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen-max-latest","name":"Qwen Max Latest","display_name":"Qwen Max Latest","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen-max-2024-09-19","name":"Qwen Max 2024 09 19","display_name":"Qwen Max 2024 09 19","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":8192},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen-max-2024-04-28","name":"Qwen Max 2024 04 28","display_name":"Qwen Max 2024 04 28","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8000,"output":2000},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-max-2024-04-03","name":"Qwen Max 2024 04 03","display_name":"Qwen Max 2024 04 03","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8000,"output":2000},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen-max-2025-01-25","name":"Qwen Max 2025 01 25","display_name":"Qwen Max 2025 01 25","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3-max-2025-09-23","name":"Qwen3 Max 20250923","display_name":"Qwen3 Max 20250923","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"reasoning":{"supported":false},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"type":"chat"},{"id":"qwen3-max-preview","name":"Qwen3 Max Preview","display_name":"Qwen3 Max Preview","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"reasoning":{"supported":true},"search":{"supported":true,"default":false,"forced_search":false,"search_strategy":"turbo"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","display_name":"Qwen3 235B A22B Thinking 2507","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","display_name":"Qwen3 235B A22B Instruct 2507","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","display_name":"Qwen3 30B A3B Instruct 2507","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":false},"type":"chat"},{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","display_name":"Qwen3 30B A3B Thinking 2507","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-30b-a3b","name":"Qwen3 30B A3B","display_name":"Qwen3 30B A3B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-4b","name":"Qwen3 4B","display_name":"Qwen3 4B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":38912,"default":38912}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-1.7b","name":"Qwen3 1.7B","display_name":"Qwen3 1.7B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":30720,"default":30720}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-0.6b","name":"Qwen3 0.6B","display_name":"Qwen3 0.6B","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":30720,"default":30720}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen3-vl-plus-2025-09-23","name":"Qwen3 VL Plus 2025 09 23","display_name":"Qwen3 VL Plus 2025 09 23","temperature":true,"attachment":false,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":32768},"reasoning":{"supported":true,"default":false,"budget":{"min":0,"max":81920,"default":81920}},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwq-plus-latest","name":"QwQ Plus Latest","display_name":"QwQ Plus Latest","temperature":true,"attachment":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":8192},"reasoning":{"supported":true,"default":true,"budget":{"min":0,"max":32768,"default":32768}},"search":{"supported":false},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"}]},"kimi-for-coding":{"id":"kimi-for-coding","api":"https://api.kimi.com/coding/v1","name":"Kimi For Coding","doc":"https://www.kimi.com/code/docs/en/kimi-code/models.html","display_name":"Kimi For Coding","models":[{"id":"kimi-for-coding-highspeed","name":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.7-code-highspeed","display_name":"Kimi For Coding HighSpeed","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"kimi-for-coding","name":"kimi-for-coding","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-09-11","last_updated":"2026-09-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k2.8-preview","display_name":"kimi-for-coding","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"k3-256k","name":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3-256K","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"canonical_model_id":"moonshotai/kimi-k3","display_name":"Kimi K3","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04","last_updated":"2026-04","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Kimi K2.7 Code","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}}},{"id":"kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","family":"kimi-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04","last_updated":"2026-04","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"display_name":"Kimi K2.7 Code Highspeed","type":"chat","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}}}]},"ollama":{"id":"ollama","name":"Ollama Cloud","display_name":"Ollama Cloud","metadata":{"source":"public-provider-conf","generated_at":"2026-09-23T07:56:05.691Z"},"models":[{"id":"alfred","name":"alfred","display_name":"alfred","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"alfred:40b","name":"alfred 40b","display_name":"alfred 40b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"all-minilm","name":"all-minilm","display_name":"all-minilm","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"all-minilm:22m","name":"all-minilm 22m","display_name":"all-minilm 22m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"all-minilm:33m","name":"all-minilm 33m","display_name":"all-minilm 33m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"athene-v2","name":"athene-v2","display_name":"athene-v2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"athene-v2:72b","name":"athene-v2 72b","display_name":"athene-v2 72b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"aya","name":"aya","display_name":"aya","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"aya-expanse","name":"aya-expanse","display_name":"aya-expanse","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"aya-expanse:32b","name":"aya-expanse 32b","display_name":"aya-expanse 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"aya-expanse:8b","name":"aya-expanse 8b","display_name":"aya-expanse 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"aya:35b","name":"aya 35b","display_name":"aya 35b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"aya:8b","name":"aya 8b","display_name":"aya 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"bakllava","name":"bakllava","display_name":"bakllava","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"bakllava:7b","name":"bakllava 7b","display_name":"bakllava 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":8192,"output":4096},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"bespoke-minicheck","name":"bespoke-minicheck","display_name":"bespoke-minicheck","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"bespoke-minicheck:7b","name":"bespoke-minicheck 7b","display_name":"bespoke-minicheck 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"bge-large","name":"bge-large","display_name":"bge-large","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"bge-large:335m","name":"bge-large 335m","display_name":"bge-large 335m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"bge-m3","name":"bge-m3","display_name":"bge-m3","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"bge-m3:567m","name":"bge-m3 567m","display_name":"bge-m3 567m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"codebooga","name":"codebooga","display_name":"codebooga","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"codebooga:34b","name":"codebooga 34b","display_name":"codebooga 34b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"codegeex4","name":"codegeex4","display_name":"codegeex4","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"codegeex4:9b","name":"codegeex4 9b","display_name":"codegeex4 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"codegemma","name":"codegemma","display_name":"codegemma","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"codegemma:2b","name":"codegemma 2b","display_name":"codegemma 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"codegemma:7b","name":"codegemma 7b","display_name":"codegemma 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"codellama","name":"codellama","display_name":"codellama","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"codellama:13b","name":"codellama 13b","display_name":"codellama 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"codellama:34b","name":"codellama 34b","display_name":"codellama 34b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"codellama:70b","name":"codellama 70b","display_name":"codellama 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"codellama:7b","name":"codellama 7b","display_name":"codellama 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"codeqwen","name":"codeqwen","display_name":"codeqwen","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"codeqwen:7b","name":"codeqwen 7b","display_name":"codeqwen 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"codestral","name":"codestral","display_name":"codestral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"codestral:22b","name":"codestral 22b","display_name":"codestral 22b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"codeup","name":"codeup","display_name":"codeup","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"codeup:13b","name":"codeup 13b","display_name":"codeup 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito","name":"cogito","display_name":"cogito","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito-2.1","name":"cogito-2.1","display_name":"cogito-2.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito-2.1:671b","name":"cogito-2.1 671b","display_name":"cogito-2.1 671b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito:14b","name":"cogito 14b","display_name":"cogito 14b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito:32b","name":"cogito 32b","display_name":"cogito 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito:3b","name":"cogito 3b","display_name":"cogito 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito:70b","name":"cogito 70b","display_name":"cogito 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"cogito:8b","name":"cogito 8b","display_name":"cogito 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-a","name":"command-a","display_name":"command-a","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-a:111b","name":"command-a 111b","display_name":"command-a 111b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r","name":"command-r","display_name":"command-r","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r-plus","name":"command-r-plus","display_name":"command-r-plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r-plus:104b","name":"command-r-plus 104b","display_name":"command-r-plus 104b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r:35b","name":"command-r 35b","display_name":"command-r 35b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r7b","name":"command-r7b","display_name":"command-r7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r7b-arabic","name":"command-r7b-arabic","display_name":"command-r7b-arabic","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r7b-arabic:7b","name":"command-r7b-arabic 7b","display_name":"command-r7b-arabic 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"command-r7b:7b","name":"command-r7b 7b","display_name":"command-r7b 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"dbrx","name":"dbrx","display_name":"dbrx","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"dbrx:132b","name":"dbrx 132b","display_name":"dbrx 132b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepcoder","name":"deepcoder","display_name":"deepcoder","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepcoder:1.5b","name":"deepcoder 1.5b","display_name":"deepcoder 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepcoder:14b","name":"deepcoder 14b","display_name":"deepcoder 14b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepscaler","name":"deepscaler","display_name":"deepscaler","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepscaler:1.5b","name":"deepscaler 1.5b","display_name":"deepscaler 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-coder","name":"deepseek-coder","display_name":"deepseek-coder","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-coder-v2","name":"deepseek-coder-v2","display_name":"deepseek-coder-v2","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-coder-v2:16b","name":"deepseek-coder-v2 16b","display_name":"deepseek-coder-v2 16b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-coder-v2:236b","name":"deepseek-coder-v2 236b","display_name":"deepseek-coder-v2 236b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-coder:1.3b","name":"deepseek-coder 1.3b","display_name":"deepseek-coder 1.3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-coder:33b","name":"deepseek-coder 33b","display_name":"deepseek-coder 33b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-coder:6.7b","name":"deepseek-coder 6.7b","display_name":"deepseek-coder 6.7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-llm","name":"deepseek-llm","display_name":"deepseek-llm","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-llm:67b","name":"deepseek-llm 67b","display_name":"deepseek-llm 67b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-llm:7b","name":"deepseek-llm 7b","display_name":"deepseek-llm 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-ocr","name":"deepseek-ocr","display_name":"deepseek-ocr","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-ocr:3b","name":"deepseek-ocr 3b","display_name":"deepseek-ocr 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-r1","name":"deepseek-r1","display_name":"deepseek-r1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-r1:1.5b","name":"deepseek-r1 1.5b","display_name":"deepseek-r1 1.5b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-r1:14b","name":"deepseek-r1 14b","display_name":"deepseek-r1 14b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-r1:32b","name":"deepseek-r1 32b","display_name":"deepseek-r1 32b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-r1:671b","name":"deepseek-r1 671b","display_name":"deepseek-r1 671b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":163840,"output":81920},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-r1:70b","name":"deepseek-r1 70b","display_name":"deepseek-r1 70b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-r1:7b","name":"deepseek-r1 7b","display_name":"deepseek-r1 7b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-r1:8b","name":"deepseek-r1 8b","display_name":"deepseek-r1 8b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v2","name":"deepseek-v2","display_name":"deepseek-v2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v2:16b","name":"deepseek-v2 16b","display_name":"deepseek-v2 16b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v2:236b","name":"deepseek-v2 236b","display_name":"deepseek-v2 236b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v2.5","name":"deepseek-v2.5","display_name":"deepseek-v2.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v2.5:236b","name":"deepseek-v2.5 236b","display_name":"deepseek-v2.5 236b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v3","name":"deepseek-v3","display_name":"deepseek-v3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v3:671b","name":"deepseek-v3 671b","display_name":"deepseek-v3 671b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v3.1","name":"deepseek-v3.1","display_name":"deepseek-v3.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v3.1:671b","name":"deepseek-v3.1 671b","display_name":"deepseek-v3.1 671b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v3.2:cloud","name":"deepseek-v3.2 cloud","display_name":"deepseek-v3.2 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v4-flash:0731-cloud","name":"deepseek-v4-flash 0731-cloud","display_name":"deepseek-v4-flash 0731-cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v4-flash:cloud","name":"deepseek-v4-flash cloud","display_name":"deepseek-v4-flash cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v4-pro:0813-cloud","name":"deepseek-v4-pro 0813-cloud","display_name":"deepseek-v4-pro 0813-cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v4-pro:cloud","name":"deepseek-v4-pro cloud","display_name":"deepseek-v4-pro cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"deepseek-v4.1-flash:cloud","name":"deepseek-v4.1-flash cloud","display_name":"deepseek-v4.1-flash cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"devstral","name":"devstral","display_name":"devstral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"devstral-2","name":"devstral-2","display_name":"devstral-2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"devstral-2:123b","name":"devstral-2 123b","display_name":"devstral-2 123b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"devstral-small-2","name":"devstral-small-2","display_name":"devstral-small-2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"devstral-small-2:24b","name":"devstral-small-2 24b","display_name":"devstral-small-2 24b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"devstral:24b","name":"devstral 24b","display_name":"devstral 24b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-llama3","name":"dolphin-llama3","display_name":"dolphin-llama3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-llama3:70b","name":"dolphin-llama3 70b","display_name":"dolphin-llama3 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-llama3:8b","name":"dolphin-llama3 8b","display_name":"dolphin-llama3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-mistral","name":"dolphin-mistral","display_name":"dolphin-mistral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-mistral:7b","name":"dolphin-mistral 7b","display_name":"dolphin-mistral 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-mixtral","name":"dolphin-mixtral","display_name":"dolphin-mixtral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-mixtral:8x22b","name":"dolphin-mixtral 8x22b","display_name":"dolphin-mixtral 8x22b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-mixtral:8x7b","name":"dolphin-mixtral 8x7b","display_name":"dolphin-mixtral 8x7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-phi","name":"dolphin-phi","display_name":"dolphin-phi","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin-phi:2.7b","name":"dolphin-phi 2.7b","display_name":"dolphin-phi 2.7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin3","name":"dolphin3","display_name":"dolphin3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphin3:8b","name":"dolphin3 8b","display_name":"dolphin3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphincoder","name":"dolphincoder","display_name":"dolphincoder","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphincoder:15b","name":"dolphincoder 15b","display_name":"dolphincoder 15b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"dolphincoder:7b","name":"dolphincoder 7b","display_name":"dolphincoder 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"duckdb-nsql","name":"duckdb-nsql","display_name":"duckdb-nsql","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"duckdb-nsql:7b","name":"duckdb-nsql 7b","display_name":"duckdb-nsql 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"embeddinggemma","name":"embeddinggemma","display_name":"embeddinggemma","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"embeddinggemma:300m","name":"embeddinggemma 300m","display_name":"embeddinggemma 300m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"everythinglm","name":"everythinglm","display_name":"everythinglm","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"everythinglm:13b","name":"everythinglm 13b","display_name":"everythinglm 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone-deep","name":"exaone-deep","display_name":"exaone-deep","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone-deep:2.4b","name":"exaone-deep 2.4b","display_name":"exaone-deep 2.4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone-deep:32b","name":"exaone-deep 32b","display_name":"exaone-deep 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone-deep:7.8b","name":"exaone-deep 7.8b","display_name":"exaone-deep 7.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone3.5","name":"exaone3.5","display_name":"exaone3.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone3.5:2.4b","name":"exaone3.5 2.4b","display_name":"exaone3.5 2.4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone3.5:32b","name":"exaone3.5 32b","display_name":"exaone3.5 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"exaone3.5:7.8b","name":"exaone3.5 7.8b","display_name":"exaone3.5 7.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon","name":"falcon","display_name":"falcon","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon:180b","name":"falcon 180b","display_name":"falcon 180b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon:40b","name":"falcon 40b","display_name":"falcon 40b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon:7b","name":"falcon 7b","display_name":"falcon 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon2","name":"falcon2","display_name":"falcon2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon2:11b","name":"falcon2 11b","display_name":"falcon2 11b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon3","name":"falcon3","display_name":"falcon3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon3:10b","name":"falcon3 10b","display_name":"falcon3 10b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon3:1b","name":"falcon3 1b","display_name":"falcon3 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon3:3b","name":"falcon3 3b","display_name":"falcon3 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"falcon3:7b","name":"falcon3 7b","display_name":"falcon3 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"firefunction-v2","name":"firefunction-v2","display_name":"firefunction-v2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"firefunction-v2:70b","name":"firefunction-v2 70b","display_name":"firefunction-v2 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"functiongemma","name":"functiongemma","display_name":"functiongemma","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"functiongemma:270m","name":"functiongemma 270m","display_name":"functiongemma 270m","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemini-3-flash-preview","name":"gemini-3-flash-preview","display_name":"gemini-3-flash-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemma","name":"gemma","display_name":"gemma","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma:2b","name":"gemma 2b","display_name":"gemma 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma:7b","name":"gemma 7b","display_name":"gemma 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma2","name":"gemma2","display_name":"gemma2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma2:27b","name":"gemma2 27b","display_name":"gemma2 27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma2:2b","name":"gemma2 2b","display_name":"gemma2 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma2:9b","name":"gemma2 9b","display_name":"gemma2 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3","name":"gemma3","display_name":"gemma3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3:12b","name":"gemma3 12b","display_name":"gemma3 12b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3:1b","name":"gemma3 1b","display_name":"gemma3 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3:270m","name":"gemma3 270m","display_name":"gemma3 270m","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3:27b","name":"gemma3 27b","display_name":"gemma3 27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3:4b","name":"gemma3 4b","display_name":"gemma3 4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3n","name":"gemma3n","display_name":"gemma3n","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3n:e2b","name":"gemma3n e2b","display_name":"gemma3n e2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma3n:e4b","name":"gemma3n e4b","display_name":"gemma3n e4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"gemma4","name":"gemma4","display_name":"gemma4","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"gemma4:12b","name":"gemma4 12b","display_name":"gemma4 12b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"gemma4:26b","name":"gemma4 26b","display_name":"gemma4 26b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"gemma4:31b","name":"gemma4:31b","display_name":"gemma4:31b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"limit":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.14,"output":0.4,"cache_read":0.05},"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning_options":[{"type":"toggle"}],"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-08","open_weights":true},{"id":"gemma4:31b-cloud","name":"gemma4 31b-cloud","display_name":"gemma4 31b-cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"gemma4:cloud","name":"gemma4 cloud","display_name":"gemma4 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"gemma4:e2b","name":"gemma4 e2b","display_name":"gemma4 e2b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"gemma4:e4b","name":"gemma4 e4b","display_name":"gemma4 e4b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"glm-4.7-flash","name":"glm-4.7-flash","display_name":"glm-4.7-flash","type":"chat","reasoning":{"supported":true},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.7:cloud","name":"glm-4.7 cloud","display_name":"glm-4.7 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"glm-5:cloud","name":"glm-5 cloud","display_name":"glm-5 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"glm-5.1:cloud","name":"glm-5.1 cloud","display_name":"glm-5.1 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":202752,"output":101376},"modalities":{"input":["text"],"output":["text"]}},{"id":"glm-5.2:cloud","name":"glm-5.2 cloud","display_name":"glm-5.2 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":999424,"output":499712},"modalities":{"input":["text"],"output":["text"]}},{"id":"glm-5.3","name":"GLM-5.3","display_name":"GLM-5.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","open_weights":true,"canonical_model_id":"zhipuai/glm-5.3"},{"id":"glm-5.3-flash","name":"GLM-5.3-Flash","display_name":"GLM-5.3-Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"limit":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"cost":{"input":0.15,"output":0.5,"cache_read":0.03},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","family":"glm-flash","attachment":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-26","last_updated":"2026-08-26","open_weights":true,"canonical_model_id":"zhipuai/glm-5.3-flash"},{"id":"glm-5.3-flash:cloud","name":"glm-5.3-flash cloud","display_name":"glm-5.3-flash cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"glm-5.3:cloud","name":"glm-5.3 cloud","display_name":"glm-5.3 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"glm-ocr","name":"glm-ocr","display_name":"glm-ocr","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"glm4","name":"glm4","display_name":"glm4","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"glm4:9b","name":"glm4 9b","display_name":"glm4 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"goliath","name":"goliath","display_name":"goliath","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"gpt-oss","name":"gpt-oss","display_name":"gpt-oss","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"gpt-oss-safeguard","name":"gpt-oss-safeguard","display_name":"gpt-oss-safeguard","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"gpt-oss-safeguard:120b","name":"gpt-oss-safeguard 120b","display_name":"gpt-oss-safeguard 120b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"gpt-oss-safeguard:20b","name":"gpt-oss-safeguard 20b","display_name":"gpt-oss-safeguard 20b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"gpt-oss:120b","name":"gpt-oss:120b","display_name":"gpt-oss:120b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.15,"output":0.6,"cache_read":0.014},"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"release_date":"2025-08-05","last_updated":"2026-01-19","open_weights":true},{"id":"gpt-oss:120b-cloud","name":"gpt-oss 120b-cloud","display_name":"gpt-oss 120b-cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"gpt-oss:20b","name":"gpt-oss:20b","display_name":"gpt-oss:20b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.07,"output":0.3,"cache_read":0.035},"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"release_date":"2025-08-05","last_updated":"2026-01-19","open_weights":true},{"id":"gpt-oss:20b-cloud","name":"gpt-oss 20b-cloud","display_name":"gpt-oss 20b-cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-code","name":"granite-code","display_name":"granite-code","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-code:20b","name":"granite-code 20b","display_name":"granite-code 20b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-code:34b","name":"granite-code 34b","display_name":"granite-code 34b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-code:3b","name":"granite-code 3b","display_name":"granite-code 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-code:8b","name":"granite-code 8b","display_name":"granite-code 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-embedding","name":"granite-embedding","display_name":"granite-embedding","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-embedding:278m","name":"granite-embedding 278m","display_name":"granite-embedding 278m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite-embedding:30m","name":"granite-embedding 30m","display_name":"granite-embedding 30m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-dense","name":"granite3-dense","display_name":"granite3-dense","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-dense:2b","name":"granite3-dense 2b","display_name":"granite3-dense 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-dense:8b","name":"granite3-dense 8b","display_name":"granite3-dense 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-guardian","name":"granite3-guardian","display_name":"granite3-guardian","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-guardian:2b","name":"granite3-guardian 2b","display_name":"granite3-guardian 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-guardian:8b","name":"granite3-guardian 8b","display_name":"granite3-guardian 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-moe","name":"granite3-moe","display_name":"granite3-moe","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-moe:1b","name":"granite3-moe 1b","display_name":"granite3-moe 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3-moe:3b","name":"granite3-moe 3b","display_name":"granite3-moe 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.1-dense","name":"granite3.1-dense","display_name":"granite3.1-dense","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.1-dense:2b","name":"granite3.1-dense 2b","display_name":"granite3.1-dense 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.1-dense:8b","name":"granite3.1-dense 8b","display_name":"granite3.1-dense 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.1-moe","name":"granite3.1-moe","display_name":"granite3.1-moe","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.1-moe:1b","name":"granite3.1-moe 1b","display_name":"granite3.1-moe 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.1-moe:3b","name":"granite3.1-moe 3b","display_name":"granite3.1-moe 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.2","name":"granite3.2","display_name":"granite3.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.2-vision","name":"granite3.2-vision","display_name":"granite3.2-vision","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"granite3.2-vision:2b","name":"granite3.2-vision 2b","display_name":"granite3.2-vision 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":8192,"output":4096},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"granite3.2:2b","name":"granite3.2 2b","display_name":"granite3.2 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.2:8b","name":"granite3.2 8b","display_name":"granite3.2 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.3","name":"granite3.3","display_name":"granite3.3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.3:2b","name":"granite3.3 2b","display_name":"granite3.3 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite3.3:8b","name":"granite3.3 8b","display_name":"granite3.3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4","name":"granite4","display_name":"granite4","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4:1b","name":"granite4 1b","display_name":"granite4 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4:350m","name":"granite4 350m","display_name":"granite4 350m","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4:3b","name":"granite4 3b","display_name":"granite4 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.1-guardian:8b","name":"granite4.1-guardian 8b","display_name":"granite4.1-guardian 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.1:30b","name":"granite4.1 30b","display_name":"granite4.1 30b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.1:3b","name":"granite4.1 3b","display_name":"granite4.1 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.1:8b","name":"granite4.1 8b","display_name":"granite4.1 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.2","name":"granite4.2","display_name":"granite4.2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.2:30b","name":"granite4.2 30b","display_name":"granite4.2 30b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.2:3b","name":"granite4.2 3b","display_name":"granite4.2 3b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"granite4.2:8b","name":"granite4.2 8b","display_name":"granite4.2 8b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"hermes3","name":"hermes3","display_name":"hermes3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"hermes3:3b","name":"hermes3 3b","display_name":"hermes3 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"hermes3:405b","name":"hermes3 405b","display_name":"hermes3 405b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"hermes3:70b","name":"hermes3 70b","display_name":"hermes3 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"hermes3:8b","name":"hermes3 8b","display_name":"hermes3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"internlm2","name":"internlm2","display_name":"internlm2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"internlm2:1.8b","name":"internlm2 1.8b","display_name":"internlm2 1.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"internlm2:1m","name":"internlm2 1m","display_name":"internlm2 1m","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"internlm2:20b","name":"internlm2 20b","display_name":"internlm2 20b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"internlm2:7b","name":"internlm2 7b","display_name":"internlm2 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"kimi-k2.5:cloud","name":"kimi-k2.5 cloud","display_name":"kimi-k2.5 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"kimi-k2.6:cloud","name":"kimi-k2.6 cloud","display_name":"kimi-k2.6 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"kimi-k2.7-code:cloud","name":"kimi-k2.7-code cloud","display_name":"kimi-k2.7-code cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"kimi-k3","name":"kimi-k3","display_name":"kimi-k3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"limit":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":3,"output":15,"cache_read":0.3},"extra_capabilities":{"reasoning":{"supported":true}},"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-27","open_weights":true,"canonical_model_id":"moonshotai/kimi-k3"},{"id":"kimi-k3:cloud","name":"kimi-k3 cloud","display_name":"kimi-k3 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"laguna-s-2.1","name":"laguna-s-2.1","display_name":"laguna-s-2.1","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"laguna-xs-2.1:latest","name":"laguna-xs-2.1 latest","display_name":"laguna-xs-2.1 latest","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"laguna-xs.2","name":"laguna-xs.2","display_name":"laguna-xs.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"lfm2","name":"lfm2","display_name":"lfm2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"lfm2:24b","name":"lfm2 24b","display_name":"lfm2 24b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"lfm2.5","name":"lfm2.5","display_name":"lfm2.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"lfm2.5-thinking","name":"lfm2.5-thinking","display_name":"lfm2.5-thinking","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"lfm2.5-thinking:1.2b","name":"lfm2.5-thinking 1.2b","display_name":"lfm2.5-thinking 1.2b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"lfm2.5:8b","name":"lfm2.5 8b","display_name":"lfm2.5 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama-guard3","name":"llama-guard3","display_name":"llama-guard3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama-guard3:1b","name":"llama-guard3 1b","display_name":"llama-guard3 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama-guard3:8b","name":"llama-guard3 8b","display_name":"llama-guard3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama-pro","name":"llama-pro","display_name":"llama-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2","name":"llama2","display_name":"llama2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2-chinese","name":"llama2-chinese","display_name":"llama2-chinese","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2-chinese:13b","name":"llama2-chinese 13b","display_name":"llama2-chinese 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2-chinese:7b","name":"llama2-chinese 7b","display_name":"llama2-chinese 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2-uncensored","name":"llama2-uncensored","display_name":"llama2-uncensored","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2-uncensored:70b","name":"llama2-uncensored 70b","display_name":"llama2-uncensored 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2-uncensored:7b","name":"llama2-uncensored 7b","display_name":"llama2-uncensored 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2:13b","name":"llama2 13b","display_name":"llama2 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2:70b","name":"llama2 70b","display_name":"llama2 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama2:7b","name":"llama2 7b","display_name":"llama2 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3","name":"llama3","display_name":"llama3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-chatqa","name":"llama3-chatqa","display_name":"llama3-chatqa","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-chatqa:70b","name":"llama3-chatqa 70b","display_name":"llama3-chatqa 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-chatqa:8b","name":"llama3-chatqa 8b","display_name":"llama3-chatqa 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-gradient","name":"llama3-gradient","display_name":"llama3-gradient","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-gradient:70b","name":"llama3-gradient 70b","display_name":"llama3-gradient 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-gradient:8b","name":"llama3-gradient 8b","display_name":"llama3-gradient 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-groq-tool-use","name":"llama3-groq-tool-use","display_name":"llama3-groq-tool-use","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-groq-tool-use:70b","name":"llama3-groq-tool-use 70b","display_name":"llama3-groq-tool-use 70b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3-groq-tool-use:8b","name":"llama3-groq-tool-use 8b","display_name":"llama3-groq-tool-use 8b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3:70b","name":"llama3 70b","display_name":"llama3 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3:8b","name":"llama3 8b","display_name":"llama3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.1","name":"llama3.1","display_name":"llama3.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.1:405b","name":"llama3.1 405b","display_name":"llama3.1 405b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.1:70b","name":"llama3.1 70b","display_name":"llama3.1 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.1:8b","name":"llama3.1 8b","display_name":"llama3.1 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.2","name":"llama3.2","display_name":"llama3.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.2-vision","name":"llama3.2-vision","display_name":"llama3.2-vision","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llama3.2-vision:11b","name":"llama3.2-vision 11b","display_name":"llama3.2-vision 11b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":16384,"output":8192},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llama3.2-vision:90b","name":"llama3.2-vision 90b","display_name":"llama3.2-vision 90b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":128000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llama3.2:1b","name":"llama3.2 1b","display_name":"llama3.2 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.2:3b","name":"llama3.2 3b","display_name":"llama3.2 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.3","name":"llama3.3","display_name":"llama3.3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama3.3:70b","name":"llama3.3 70b","display_name":"llama3.3 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"llama4","name":"llama4","display_name":"llama4","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":true,"limit":{"context":10485760,"output":5242880},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llama4:128x17b","name":"llama4 128x17b","display_name":"llama4 128x17b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":true,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llama4:16x17b","name":"llama4 16x17b","display_name":"llama4 16x17b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":true,"limit":{"context":10485760,"output":5242880},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava","name":"llava","display_name":"llava","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava-llama3","name":"llava-llama3","display_name":"llava-llama3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava-llama3:8b","name":"llava-llama3 8b","display_name":"llava-llama3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":16384,"output":8192},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava-phi3","name":"llava-phi3","display_name":"llava-phi3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava-phi3:3.8b","name":"llava-phi3 3.8b","display_name":"llava-phi3 3.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":4096,"output":2048},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava:13b","name":"llava 13b","display_name":"llava 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":16384,"output":8192},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava:34b","name":"llava 34b","display_name":"llava 34b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":16384,"output":8192},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"llava:7b","name":"llava 7b","display_name":"llava 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":8192,"output":4096},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"magicoder","name":"magicoder","display_name":"magicoder","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"magicoder:7b","name":"magicoder 7b","display_name":"magicoder 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"magistral","name":"magistral","display_name":"magistral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"magistral:24b","name":"magistral 24b","display_name":"magistral 24b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"marco-o1","name":"marco-o1","display_name":"marco-o1","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"marco-o1:7b","name":"marco-o1 7b","display_name":"marco-o1 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"mathstral","name":"mathstral","display_name":"mathstral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mathstral:7b","name":"mathstral 7b","display_name":"mathstral 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"medgemma","name":"medgemma","display_name":"medgemma","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"medgemma:27b","name":"medgemma 27b","display_name":"medgemma 27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"medgemma:4b","name":"medgemma 4b","display_name":"medgemma 4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"medgemma1.5","name":"medgemma1.5","display_name":"medgemma1.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"medgemma1.5:4b","name":"medgemma1.5 4b","display_name":"medgemma1.5 4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"meditron","name":"meditron","display_name":"meditron","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"meditron:70b","name":"meditron 70b","display_name":"meditron 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"meditron:7b","name":"meditron 7b","display_name":"meditron 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"medllama2","name":"medllama2","display_name":"medllama2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"medllama2:7b","name":"medllama2 7b","display_name":"medllama2 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"megadolphin","name":"megadolphin","display_name":"megadolphin","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"megadolphin:120b","name":"megadolphin 120b","display_name":"megadolphin 120b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"minicpm-v","name":"minicpm-v","display_name":"minicpm-v","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"minicpm-v:8b","name":"minicpm-v 8b","display_name":"minicpm-v 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"minicpm-v4.5","name":"minicpm-v4.5","display_name":"minicpm-v4.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"minicpm-v4.5:8b","name":"minicpm-v4.5 8b","display_name":"minicpm-v4.5 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"minicpm-v4.6","name":"minicpm-v4.6","display_name":"minicpm-v4.6","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"minicpm-v4.6:1b","name":"minicpm-v4.6 1b","display_name":"minicpm-v4.6 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"minimax-m2.1:cloud","name":"minimax-m2.1 cloud","display_name":"minimax-m2.1 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"minimax-m2.5:cloud","name":"minimax-m2.5 cloud","display_name":"minimax-m2.5 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"minimax-m2.7:cloud","name":"minimax-m2.7 cloud","display_name":"minimax-m2.7 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":204800,"output":102400},"modalities":{"input":["text"],"output":["text"]}},{"id":"minimax-m3:cloud","name":"minimax-m3 cloud","display_name":"minimax-m3 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":524288,"output":262144},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"ministral-3","name":"ministral-3","display_name":"ministral-3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"ministral-3:14b","name":"ministral-3 14b","display_name":"ministral-3 14b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"ministral-3:3b","name":"ministral-3 3b","display_name":"ministral-3 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"ministral-3:8b","name":"ministral-3 8b","display_name":"ministral-3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral","name":"mistral","display_name":"mistral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-large","name":"mistral-large","display_name":"mistral-large","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-large-3:675b-cloud","name":"mistral-large-3 675b-cloud","display_name":"mistral-large-3 675b-cloud","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"mistral-large:123b","name":"mistral-large 123b","display_name":"mistral-large 123b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-medium-3.5","name":"mistral-medium-3.5","display_name":"mistral-medium-3.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-medium-3.5:128b","name":"mistral-medium-3.5 128b","display_name":"mistral-medium-3.5 128b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-nemo","name":"mistral-nemo","display_name":"mistral-nemo","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-nemo:12b","name":"mistral-nemo 12b","display_name":"mistral-nemo 12b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-openorca","name":"mistral-openorca","display_name":"mistral-openorca","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-openorca:7b","name":"mistral-openorca 7b","display_name":"mistral-openorca 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-small","name":"mistral-small","display_name":"mistral-small","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-small:22b","name":"mistral-small 22b","display_name":"mistral-small 22b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-small:24b","name":"mistral-small 24b","display_name":"mistral-small 24b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-small3.1","name":"mistral-small3.1","display_name":"mistral-small3.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-small3.1:24b","name":"mistral-small3.1 24b","display_name":"mistral-small3.1 24b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-small3.2","name":"mistral-small3.2","display_name":"mistral-small3.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral-small3.2:24b","name":"mistral-small3.2 24b","display_name":"mistral-small3.2 24b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistral:7b","name":"mistral 7b","display_name":"mistral 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistrallite","name":"mistrallite","display_name":"mistrallite","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mistrallite:7b","name":"mistrallite 7b","display_name":"mistrallite 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"mixtral","name":"mixtral","display_name":"mixtral","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"mixtral:8x22b","name":"mixtral 8x22b","display_name":"mixtral 8x22b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"mixtral:8x7b","name":"mixtral 8x7b","display_name":"mixtral 8x7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"moondream","name":"moondream","display_name":"moondream","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":2048,"output":1024},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"moondream:1.8b","name":"moondream 1.8b","display_name":"moondream 1.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":2048,"output":1024},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"muse-glimmer","name":"muse-glimmer","display_name":"muse-glimmer","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"muse-glimmer:30b","name":"muse-glimmer 30b","display_name":"muse-glimmer 30b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"mxbai-embed-large","name":"mxbai-embed-large","display_name":"mxbai-embed-large","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"mxbai-embed-large:335m","name":"mxbai-embed-large 335m","display_name":"mxbai-embed-large 335m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron","name":"nemotron","display_name":"nemotron","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3-nano","name":"nemotron-3-nano","display_name":"nemotron-3-nano","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3-nano:30b","name":"nemotron-3-nano:30b","display_name":"nemotron-3-nano:30b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.06,"output":0.24},"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning_options":[{"type":"toggle"}],"temperature":true,"release_date":"2025-12-15","last_updated":"2026-01-19","open_weights":true,"canonical_model_id":"nvidia/nemotron-3-nano-30b-a3b"},{"id":"nemotron-3-nano:30b-cloud","name":"nemotron-3-nano 30b-cloud","display_name":"nemotron-3-nano 30b-cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3-nano:4b","name":"nemotron-3-nano 4b","display_name":"nemotron-3-nano 4b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3-super","name":"nemotron-3-super","display_name":"nemotron-3-super","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"limit":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.015,"output":0.6,"cache_read":0.015},"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning_options":[{"type":"toggle"}],"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-12","open_weights":true,"canonical_model_id":"nvidia/nemotron-3-super-120b-a12b"},{"id":"nemotron-3-super:120b","name":"nemotron-3-super 120b","display_name":"nemotron-3-super 120b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3-super:cloud","name":"nemotron-3-super cloud","display_name":"nemotron-3-super cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3-ultra:cloud","name":"nemotron-3-ultra cloud","display_name":"nemotron-3-ultra cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3.5-lightning","name":"nemotron-3.5-lightning","display_name":"nemotron-3.5-lightning","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3.5-lightning:30b","name":"nemotron-3.5-lightning 30b","display_name":"nemotron-3.5-lightning 30b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":1048576,"output":524288},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-cascade-2","name":"nemotron-cascade-2","display_name":"nemotron-cascade-2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-cascade-2:30b","name":"nemotron-cascade-2 30b","display_name":"nemotron-cascade-2 30b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-mini","name":"nemotron-mini","display_name":"nemotron-mini","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-mini:4b","name":"nemotron-mini 4b","display_name":"nemotron-mini 4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron:70b","name":"nemotron 70b","display_name":"nemotron 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron3:33b","name":"nemotron3 33b","display_name":"nemotron3 33b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"neural-chat","name":"neural-chat","display_name":"neural-chat","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"neural-chat:7b","name":"neural-chat 7b","display_name":"neural-chat 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"nexusraven","name":"nexusraven","display_name":"nexusraven","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nexusraven:13b","name":"nexusraven 13b","display_name":"nexusraven 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"nomic-embed-text","name":"nomic-embed-text","display_name":"nomic-embed-text","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nomic-embed-text-v2-moe","name":"nomic-embed-text-v2-moe","display_name":"nomic-embed-text-v2-moe","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"north-mini-code-1.0","name":"north-mini-code-1.0","display_name":"north-mini-code-1.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"notus","name":"notus","display_name":"notus","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"notus:7b","name":"notus 7b","display_name":"notus 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"notux","name":"notux","display_name":"notux","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"notux:8x7b","name":"notux 8x7b","display_name":"notux 8x7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes","name":"nous-hermes","display_name":"nous-hermes","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes:13b","name":"nous-hermes 13b","display_name":"nous-hermes 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes:7b","name":"nous-hermes 7b","display_name":"nous-hermes 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes2","name":"nous-hermes2","display_name":"nous-hermes2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes2-mixtral","name":"nous-hermes2-mixtral","display_name":"nous-hermes2-mixtral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes2-mixtral:8x7b","name":"nous-hermes2-mixtral 8x7b","display_name":"nous-hermes2-mixtral 8x7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes2:10.7b","name":"nous-hermes2 10.7b","display_name":"nous-hermes2 10.7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nous-hermes2:34b","name":"nous-hermes2 34b","display_name":"nous-hermes2 34b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nuextract","name":"nuextract","display_name":"nuextract","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"nuextract:3.8b","name":"nuextract 3.8b","display_name":"nuextract 3.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo-3","name":"olmo-3","display_name":"olmo-3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo-3:32b","name":"olmo-3 32b","display_name":"olmo-3 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo-3:7b","name":"olmo-3 7b","display_name":"olmo-3 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo-3.1","name":"olmo-3.1","display_name":"olmo-3.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo-3.1:32b","name":"olmo-3.1 32b","display_name":"olmo-3.1 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo2","name":"olmo2","display_name":"olmo2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo2:13b","name":"olmo2 13b","display_name":"olmo2 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"olmo2:7b","name":"olmo2 7b","display_name":"olmo2 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"open-orca-platypus2","name":"open-orca-platypus2","display_name":"open-orca-platypus2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"open-orca-platypus2:13b","name":"open-orca-platypus2 13b","display_name":"open-orca-platypus2 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"openchat","name":"openchat","display_name":"openchat","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"openchat:7b","name":"openchat 7b","display_name":"openchat 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"opencoder","name":"opencoder","display_name":"opencoder","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"opencoder:1.5b","name":"opencoder 1.5b","display_name":"opencoder 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"opencoder:8b","name":"opencoder 8b","display_name":"opencoder 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"openhermes","name":"openhermes","display_name":"openhermes","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"openthinker","name":"openthinker","display_name":"openthinker","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"openthinker:32b","name":"openthinker 32b","display_name":"openthinker 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"openthinker:7b","name":"openthinker 7b","display_name":"openthinker 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca-mini","name":"orca-mini","display_name":"orca-mini","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca-mini:13b","name":"orca-mini 13b","display_name":"orca-mini 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca-mini:3b","name":"orca-mini 3b","display_name":"orca-mini 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca-mini:70b","name":"orca-mini 70b","display_name":"orca-mini 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca-mini:7b","name":"orca-mini 7b","display_name":"orca-mini 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca2","name":"orca2","display_name":"orca2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca2:13b","name":"orca2 13b","display_name":"orca2 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"orca2:7b","name":"orca2 7b","display_name":"orca2 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"ornith-1.5","name":"ornith-1.5","display_name":"ornith-1.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"ornith-1.5:35b","name":"ornith-1.5 35b","display_name":"ornith-1.5 35b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"ornith-1.5:397b","name":"ornith-1.5 397b","display_name":"ornith-1.5 397b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"ornith-1.5:9b","name":"ornith-1.5 9b","display_name":"ornith-1.5 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"ornith:35b","name":"ornith 35b","display_name":"ornith 35b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"ornith:9b","name":"ornith 9b","display_name":"ornith 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"ornith:latest","name":"ornith latest","display_name":"ornith latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"paraphrase-multilingual","name":"paraphrase-multilingual","display_name":"paraphrase-multilingual","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"paraphrase-multilingual:278m","name":"paraphrase-multilingual 278m","display_name":"paraphrase-multilingual 278m","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi","name":"phi","display_name":"phi","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi:2.7b","name":"phi 2.7b","display_name":"phi 2.7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi3","name":"phi3","display_name":"phi3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi3:14b","name":"phi3 14b","display_name":"phi3 14b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi3:3.8b","name":"phi3 3.8b","display_name":"phi3 3.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi3.5","name":"phi3.5","display_name":"phi3.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi3.5:3.8b","name":"phi3.5 3.8b","display_name":"phi3.5 3.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4","name":"phi4","display_name":"phi4","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4-mini","name":"phi4-mini","display_name":"phi4-mini","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4-mini-reasoning","name":"phi4-mini-reasoning","display_name":"phi4-mini-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4-mini-reasoning:3.8b","name":"phi4-mini-reasoning 3.8b","display_name":"phi4-mini-reasoning 3.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4-mini:3.8b","name":"phi4-mini 3.8b","display_name":"phi4-mini 3.8b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4-reasoning","name":"phi4-reasoning","display_name":"phi4-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4-reasoning:14b","name":"phi4-reasoning 14b","display_name":"phi4-reasoning 14b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"phi4:14b","name":"phi4 14b","display_name":"phi4 14b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"phind-codellama","name":"phind-codellama","display_name":"phind-codellama","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"phind-codellama:34b","name":"phind-codellama 34b","display_name":"phind-codellama 34b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen","name":"qwen","display_name":"qwen","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:0.5b","name":"qwen 0.5b","display_name":"qwen 0.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:1.8b","name":"qwen 1.8b","display_name":"qwen 1.8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:110b","name":"qwen 110b","display_name":"qwen 110b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:14b","name":"qwen 14b","display_name":"qwen 14b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:32b","name":"qwen 32b","display_name":"qwen 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:4b","name":"qwen 4b","display_name":"qwen 4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:72b","name":"qwen 72b","display_name":"qwen 72b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen:7b","name":"qwen 7b","display_name":"qwen 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2","name":"qwen2","display_name":"qwen2","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2-math","name":"qwen2-math","display_name":"qwen2-math","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2-math:1.5b","name":"qwen2-math 1.5b","display_name":"qwen2-math 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2-math:72b","name":"qwen2-math 72b","display_name":"qwen2-math 72b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2-math:7b","name":"qwen2-math 7b","display_name":"qwen2-math 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2:0.5b","name":"qwen2 0.5b","display_name":"qwen2 0.5b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2:1.5b","name":"qwen2 1.5b","display_name":"qwen2 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2:72b","name":"qwen2 72b","display_name":"qwen2 72b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2:7b","name":"qwen2 7b","display_name":"qwen2 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5","name":"qwen2.5","display_name":"qwen2.5","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5-coder","name":"qwen2.5-coder","display_name":"qwen2.5-coder","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5-coder:0.5b","name":"qwen2.5-coder 0.5b","display_name":"qwen2.5-coder 0.5b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5-coder:1.5b","name":"qwen2.5-coder 1.5b","display_name":"qwen2.5-coder 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5-coder:14b","name":"qwen2.5-coder 14b","display_name":"qwen2.5-coder 14b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5-coder:32b","name":"qwen2.5-coder 32b","display_name":"qwen2.5-coder 32b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5-coder:3b","name":"qwen2.5-coder 3b","display_name":"qwen2.5-coder 3b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5-coder:7b","name":"qwen2.5-coder 7b","display_name":"qwen2.5-coder 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5:0.5b","name":"qwen2.5 0.5b","display_name":"qwen2.5 0.5b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5:1.5b","name":"qwen2.5 1.5b","display_name":"qwen2.5 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5:14b","name":"qwen2.5 14b","display_name":"qwen2.5 14b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5:32b","name":"qwen2.5 32b","display_name":"qwen2.5 32b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5:3b","name":"qwen2.5 3b","display_name":"qwen2.5 3b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5:72b","name":"qwen2.5 72b","display_name":"qwen2.5 72b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5:7b","name":"qwen2.5 7b","display_name":"qwen2.5 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5vl","name":"qwen2.5vl","display_name":"qwen2.5vl","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5vl:32b","name":"qwen2.5vl 32b","display_name":"qwen2.5vl 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5vl:3b","name":"qwen2.5vl 3b","display_name":"qwen2.5vl 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5vl:72b","name":"qwen2.5vl 72b","display_name":"qwen2.5vl 72b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen2.5vl:7b","name":"qwen2.5vl 7b","display_name":"qwen2.5vl 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3","name":"qwen3","display_name":"qwen3","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-coder","name":"qwen3-coder","display_name":"qwen3-coder","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-coder-next","name":"qwen3-coder-next","display_name":"qwen3-coder-next","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-coder:30b","name":"qwen3-coder 30b","display_name":"qwen3-coder 30b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-coder:480b","name":"qwen3-coder 480b","display_name":"qwen3-coder 480b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-embedding","name":"qwen3-embedding","display_name":"qwen3-embedding","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-embedding:0.6b","name":"qwen3-embedding 0.6b","display_name":"qwen3-embedding 0.6b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-embedding:4b","name":"qwen3-embedding 4b","display_name":"qwen3-embedding 4b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-embedding:8b","name":"qwen3-embedding 8b","display_name":"qwen3-embedding 8b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-next","name":"qwen3-next","display_name":"qwen3-next","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-next:80b","name":"qwen3-next 80b","display_name":"qwen3-next 80b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-vl","name":"qwen3-vl","display_name":"qwen3-vl","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-vl:235b","name":"qwen3-vl 235b","display_name":"qwen3-vl 235b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-vl:2b","name":"qwen3-vl 2b","display_name":"qwen3-vl 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-vl:30b","name":"qwen3-vl 30b","display_name":"qwen3-vl 30b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-vl:32b","name":"qwen3-vl 32b","display_name":"qwen3-vl 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-vl:4b","name":"qwen3-vl 4b","display_name":"qwen3-vl 4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3-vl:8b","name":"qwen3-vl 8b","display_name":"qwen3-vl 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:0.6b","name":"qwen3 0.6b","display_name":"qwen3 0.6b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:1.7b","name":"qwen3 1.7b","display_name":"qwen3 1.7b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:14b","name":"qwen3 14b","display_name":"qwen3 14b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:235b","name":"qwen3 235b","display_name":"qwen3 235b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:30b","name":"qwen3 30b","display_name":"qwen3 30b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:32b","name":"qwen3 32b","display_name":"qwen3 32b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:4b","name":"qwen3 4b","display_name":"qwen3 4b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3:8b","name":"qwen3 8b","display_name":"qwen3 8b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":false,"limit":{"context":40960,"output":20480},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3.5","name":"qwen3.5","display_name":"qwen3.5","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:0.8b","name":"qwen3.5 0.8b","display_name":"qwen3.5 0.8b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:122b","name":"qwen3.5 122b","display_name":"qwen3.5 122b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:27b","name":"qwen3.5 27b","display_name":"qwen3.5 27b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:2b","name":"qwen3.5 2b","display_name":"qwen3.5 2b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:35b","name":"qwen3.5 35b","display_name":"qwen3.5 35b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:397b-cloud","name":"qwen3.5 397b-cloud","display_name":"qwen3.5 397b-cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:4b","name":"qwen3.5 4b","display_name":"qwen3.5 4b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:9b","name":"qwen3.5 9b","display_name":"qwen3.5 9b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.5:cloud","name":"qwen3.5 cloud","display_name":"qwen3.5 cloud","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.6","name":"qwen3.6","display_name":"qwen3.6","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3.6:27b","name":"qwen3.6 27b","display_name":"qwen3.6 27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3.6:35b","name":"qwen3.6 35b","display_name":"qwen3.6 35b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwen3.8","name":"qwen3.8","display_name":"qwen3.8","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.8-flash-next","name":"qwen3.8-flash-next","display_name":"qwen3.8-flash-next","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwen3.8:27b","name":"qwen3.8 27b","display_name":"qwen3.8 27b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"limit":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]}},{"id":"qwq","name":"qwq","display_name":"qwq","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"qwq:32b","name":"qwq 32b","display_name":"qwq 32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"r1-1776","name":"r1-1776","display_name":"r1-1776","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"r1-1776:671b","name":"r1-1776 671b","display_name":"r1-1776 671b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":false,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"r1-1776:70b","name":"r1-1776 70b","display_name":"r1-1776 70b","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"reader-lm","name":"reader-lm","display_name":"reader-lm","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]}},{"id":"reader-lm:0.5b","name":"reader-lm 0.5b","display_name":"reader-lm 0.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]}},{"id":"reader-lm:1.5b","name":"reader-lm 1.5b","display_name":"reader-lm 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]}},{"id":"reflection","name":"reflection","display_name":"reflection","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"reflection:70b","name":"reflection 70b","display_name":"reflection 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"rnj-1","name":"rnj-1","display_name":"rnj-1","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"rnj-1:8b","name":"rnj-1 8b","display_name":"rnj-1 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"sailor2","name":"sailor2","display_name":"sailor2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"sailor2:1b","name":"sailor2 1b","display_name":"sailor2 1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"sailor2:20b","name":"sailor2 20b","display_name":"sailor2 20b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"sailor2:8b","name":"sailor2 8b","display_name":"sailor2 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"samantha-mistral","name":"samantha-mistral","display_name":"samantha-mistral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"samantha-mistral:7b","name":"samantha-mistral 7b","display_name":"samantha-mistral 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"shieldgemma","name":"shieldgemma","display_name":"shieldgemma","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"shieldgemma:27b","name":"shieldgemma 27b","display_name":"shieldgemma 27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"shieldgemma:2b","name":"shieldgemma 2b","display_name":"shieldgemma 2b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"shieldgemma:9b","name":"shieldgemma 9b","display_name":"shieldgemma 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"smallthinker","name":"smallthinker","display_name":"smallthinker","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"smallthinker:3b","name":"smallthinker 3b","display_name":"smallthinker 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm","name":"smollm","display_name":"smollm","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm:1.7b","name":"smollm 1.7b","display_name":"smollm 1.7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm:135m","name":"smollm 135m","display_name":"smollm 135m","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm:360m","name":"smollm 360m","display_name":"smollm 360m","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm2","name":"smollm2","display_name":"smollm2","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm2:1.7b","name":"smollm2 1.7b","display_name":"smollm2 1.7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm2:135m","name":"smollm2 135m","display_name":"smollm2 135m","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"smollm2:360m","name":"smollm2 360m","display_name":"smollm2 360m","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed","name":"snowflake-arctic-embed","display_name":"snowflake-arctic-embed","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed:110m","name":"snowflake-arctic-embed 110m","display_name":"snowflake-arctic-embed 110m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed:137m","name":"snowflake-arctic-embed 137m","display_name":"snowflake-arctic-embed 137m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed:22m","name":"snowflake-arctic-embed 22m","display_name":"snowflake-arctic-embed 22m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed:335m","name":"snowflake-arctic-embed 335m","display_name":"snowflake-arctic-embed 335m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed:33m","name":"snowflake-arctic-embed 33m","display_name":"snowflake-arctic-embed 33m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed2","name":"snowflake-arctic-embed2","display_name":"snowflake-arctic-embed2","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"snowflake-arctic-embed2:568m","name":"snowflake-arctic-embed2 568m","display_name":"snowflake-arctic-embed2 568m","type":"embedding","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"solar","name":"solar","display_name":"solar","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"solar-pro","name":"solar-pro","display_name":"solar-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"solar-pro:22b","name":"solar-pro 22b","display_name":"solar-pro 22b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"solar:10.7b","name":"solar 10.7b","display_name":"solar 10.7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"sqlcoder","name":"sqlcoder","display_name":"sqlcoder","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"sqlcoder:15b","name":"sqlcoder 15b","display_name":"sqlcoder 15b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"sqlcoder:7b","name":"sqlcoder 7b","display_name":"sqlcoder 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"stable-beluga","name":"stable-beluga","display_name":"stable-beluga","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"stable-beluga:13b","name":"stable-beluga 13b","display_name":"stable-beluga 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"stable-beluga:70b","name":"stable-beluga 70b","display_name":"stable-beluga 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"stable-beluga:7b","name":"stable-beluga 7b","display_name":"stable-beluga 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"stable-code","name":"stable-code","display_name":"stable-code","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"stable-code:3b","name":"stable-code 3b","display_name":"stable-code 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"stablelm-zephyr","name":"stablelm-zephyr","display_name":"stablelm-zephyr","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"stablelm-zephyr:3b","name":"stablelm-zephyr 3b","display_name":"stablelm-zephyr 3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"stablelm2","name":"stablelm2","display_name":"stablelm2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"stablelm2:1.6b","name":"stablelm2 1.6b","display_name":"stablelm2 1.6b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"stablelm2:12b","name":"stablelm2 12b","display_name":"stablelm2 12b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder","name":"starcoder","display_name":"starcoder","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder:15b","name":"starcoder 15b","display_name":"starcoder 15b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder:1b","name":"starcoder 1b","display_name":"starcoder 1b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder:3b","name":"starcoder 3b","display_name":"starcoder 3b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder:7b","name":"starcoder 7b","display_name":"starcoder 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder2","name":"starcoder2","display_name":"starcoder2","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder2:15b","name":"starcoder2 15b","display_name":"starcoder2 15b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder2:3b","name":"starcoder2 3b","display_name":"starcoder2 3b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"starcoder2:7b","name":"starcoder2 7b","display_name":"starcoder2 7b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"starling-lm","name":"starling-lm","display_name":"starling-lm","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"starling-lm:7b","name":"starling-lm 7b","display_name":"starling-lm 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"tinydolphin","name":"tinydolphin","display_name":"tinydolphin","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"tinydolphin:1.1b","name":"tinydolphin 1.1b","display_name":"tinydolphin 1.1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"tinyllama","name":"tinyllama","display_name":"tinyllama","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"tinyllama:1.1b","name":"tinyllama 1.1b","display_name":"tinyllama 1.1b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"translategemma","name":"translategemma","display_name":"translategemma","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"translategemma:12b","name":"translategemma 12b","display_name":"translategemma 12b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"translategemma:27b","name":"translategemma 27b","display_name":"translategemma 27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"translategemma:4b","name":"translategemma 4b","display_name":"translategemma 4b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"tulu3","name":"tulu3","display_name":"tulu3","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"tulu3:70b","name":"tulu3 70b","display_name":"tulu3 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"tulu3:8b","name":"tulu3 8b","display_name":"tulu3 8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"vicuna","name":"vicuna","display_name":"vicuna","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"vicuna:13b","name":"vicuna 13b","display_name":"vicuna 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"vicuna:33b","name":"vicuna 33b","display_name":"vicuna 33b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"vicuna:7b","name":"vicuna 7b","display_name":"vicuna 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-math","name":"wizard-math","display_name":"wizard-math","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-math:13b","name":"wizard-math 13b","display_name":"wizard-math 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-math:70b","name":"wizard-math 70b","display_name":"wizard-math 70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-math:7b","name":"wizard-math 7b","display_name":"wizard-math 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-vicuna","name":"wizard-vicuna","display_name":"wizard-vicuna","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-vicuna-uncensored","name":"wizard-vicuna-uncensored","display_name":"wizard-vicuna-uncensored","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-vicuna-uncensored:13b","name":"wizard-vicuna-uncensored 13b","display_name":"wizard-vicuna-uncensored 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-vicuna-uncensored:30b","name":"wizard-vicuna-uncensored 30b","display_name":"wizard-vicuna-uncensored 30b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-vicuna-uncensored:7b","name":"wizard-vicuna-uncensored 7b","display_name":"wizard-vicuna-uncensored 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizard-vicuna:13b","name":"wizard-vicuna 13b","display_name":"wizard-vicuna 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardcoder","name":"wizardcoder","display_name":"wizardcoder","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardcoder:33b","name":"wizardcoder 33b","display_name":"wizardcoder 33b","type":"chat","reasoning":{"supported":false},"tool_call":true,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardlm-uncensored","name":"wizardlm-uncensored","display_name":"wizardlm-uncensored","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardlm-uncensored:13b","name":"wizardlm-uncensored 13b","display_name":"wizardlm-uncensored 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardlm:7b-q2_K","name":"wizardlm 7b-q2_K","display_name":"wizardlm 7b-q2_K","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":2048,"output":1024},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardlm2","name":"wizardlm2","display_name":"wizardlm2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardlm2:7b","name":"wizardlm2 7b","display_name":"wizardlm2 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]}},{"id":"wizardlm2:8x22b","name":"wizardlm2 8x22b","display_name":"wizardlm2 8x22b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":65536,"output":32768},"modalities":{"input":["text"],"output":["text"]}},{"id":"xwinlm","name":"xwinlm","display_name":"xwinlm","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"xwinlm:13b","name":"xwinlm 13b","display_name":"xwinlm 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"xwinlm:7b","name":"xwinlm 7b","display_name":"xwinlm 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"yarn-llama2","name":"yarn-llama2","display_name":"yarn-llama2","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"yarn-llama2:13b","name":"yarn-llama2 13b","display_name":"yarn-llama2 13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"yarn-llama2:7b","name":"yarn-llama2 7b","display_name":"yarn-llama2 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"yarn-mistral","name":"yarn-mistral","display_name":"yarn-mistral","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"yarn-mistral:7b","name":"yarn-mistral 7b","display_name":"yarn-mistral 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"yi","name":"yi","display_name":"yi","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"yi-coder","name":"yi-coder","display_name":"yi-coder","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"yi-coder:1.5b","name":"yi-coder 1.5b","display_name":"yi-coder 1.5b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"yi-coder:9b","name":"yi-coder 9b","display_name":"yi-coder 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]}},{"id":"yi:34b","name":"yi 34b","display_name":"yi 34b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"yi:6b","name":"yi 6b","display_name":"yi 6b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"yi:9b","name":"yi 9b","display_name":"yi 9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":16384,"output":8192},"modalities":{"input":["text"],"output":["text"]}},{"id":"zephyr","name":"zephyr","display_name":"zephyr","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":4096,"output":2048},"modalities":{"input":["text"],"output":["text"]}},{"id":"zephyr:141b","name":"zephyr 141b","display_name":"zephyr 141b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]}},{"id":"zephyr:7b","name":"zephyr 7b","display_name":"zephyr 7b","type":"chat","reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]}},{"id":"nemotron-3-ultra","name":"nemotron-3-ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.1,"output":3,"cache_read":0.1},"canonical_model_id":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"nemotron-3-ultra","type":"chat"},{"id":"mistral-large-4","name":"Mistral Large 4","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","family":"mistral-large","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-10-06","last_updated":"2026-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":262144},"cost":{"input":1.36,"output":4.18,"cache_read":0.14},"canonical_model_id":"mistral/mistral-large-4","display_name":"Mistral Large 4","type":"chat"},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek V4.1 Flash","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"minimax-m2.5","name":"minimax-m2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[],"tool_call":true,"knowledge":"2025-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"display_name":"minimax-m2.5","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"kimi-k2.6","name":"kimi-k2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"display_name":"kimi-k2.6","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"qwen3.5:397b","name":"qwen3.5:397b","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"release_date":"2026-02-15","last_updated":"2026-02-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"display_name":"qwen3.5:397b","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"deepseek-v4.1-flash:1017","name":"DeepSeek V4.1 Flash 1017","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","family":"deepseek-flash","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-10-17","last_updated":"2026-10-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.6,"cache_read":0.003},"canonical_model_id":"deepseek/deepseek-v4.1-flash-1017","display_name":"DeepSeek V4.1 Flash 1017","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"kimi-k2.5","name":"kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"display_name":"kimi-k2.5","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"mistral-large-3:675b","name":"mistral-large-3:675b","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":{"supported":false},"tool_call":true,"release_date":"2025-12-02","last_updated":"2026-01-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"display_name":"mistral-large-3:675b","type":"chat"},{"id":"minimax-m2.7","name":"minimax-m2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"display_name":"minimax-m2.7","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"deepseek-v4-pro:0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"canonical_model_id":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek V4 Pro 0813","type":"chat"},{"id":"minimax-m3","name":"minimax-m3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"display_name":"minimax-m3","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"deepseek-v4-flash:0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"canonical_model_id":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek V4 Flash 0731","type":"chat"},{"id":"glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":976000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"canonical_model_id":"zhipuai/glm-5.2","display_name":"GLM-5.2","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"glm-5.1","name":"glm-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-03-27","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"display_name":"glm-5.1","extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}},"type":"chat"},{"id":"deepseek-v4-pro","name":"deepseek-v4-pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"display_name":"deepseek-v4-pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"},{"id":"kimi-k2.7-code","name":"kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"canonical_model_id":"moonshotai/kimi-k2.7-code","display_name":"kimi-k2.7-code","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"muse-spark-open","name":"Muse Spark Open","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","family":"muse","attachment":true,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-10-15","last_updated":"2026-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"canonical_model_id":"meta/muse-spark-open","display_name":"Muse Spark Open","type":"chat"},{"id":"deepseek-v4-flash","name":"deepseek-v4-flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":{"supported":true,"default":true},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"display_name":"deepseek-v4-flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}},"type":"chat"}],"api":"https://ollama.com/v1","doc":"https://docs.ollama.com/cloud"},"burncloud":{"id":"burncloud","models":[{"id":"openai/gpt-4-turbo","name":"OpenAI GPT-4 Turbo","display_name":"GPT-4 Turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":8,"output":24},"limit":{"context":128000},"metadata":{"discount":"20% off official list"},"attachment":true,"temperature":true},{"id":"openai/o4-mini","name":"OpenAI o4-mini","display_name":"o4-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.88,"output":3.52},"limit":{"output":100000},"attachment":true,"temperature":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3","name":"OpenAI o3","display_name":"o3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":8,"output":35},"limit":{"output":100000},"attachment":true,"temperature":true,"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"OpenAI o3-mini","display_name":"o3-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.88,"output":3.52},"limit":{"output":100000},"attachment":true,"temperature":true,"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1","name":"OpenAI o1","display_name":"o1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":12,"output":48},"limit":{"output":100000},"attachment":true,"temperature":true,"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1-mini","name":"OpenAI o1-mini","display_name":"o1-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.88,"output":3.52},"limit":{"output":65536},"attachment":true,"temperature":true,"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/o1-pro","name":"OpenAI o1-pro","display_name":"o1-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":120,"output":480},"limit":{"output":100000},"attachment":true,"temperature":true,"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-4.1","name":"OpenAI GPT-4.1","display_name":"GPT-4.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.6,"output":6.4},"limit":{"output":32768},"attachment":true,"temperature":true},{"id":"openai/gpt-4o","name":"OpenAI GPT-4o","display_name":"GPT-4o","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2,"output":8},"limit":{"context":128000,"output":16384},"attachment":true,"temperature":true},{"id":"openai/gpt-4o-audio","name":"OpenAI GPT-4o Audio","display_name":"GPT-4o Audio","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":false,"modalities":{"input":["text","audio"],"output":["text","audio"]},"cost":{"input":2,"output":8},"limit":{"output":16384},"attachment":true,"temperature":true},{"id":"openai/gpt-4o-mini","name":"OpenAI GPT-4o mini","display_name":"GPT-4o mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.12,"output":0.48},"limit":{"context":128000,"output":16384},"attachment":true,"temperature":true},{"id":"openai/gpt-4o-mini-audio","name":"OpenAI GPT-4o mini Audio","display_name":"GPT-4o mini Audio","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","audio"],"output":["text","audio"]},"cost":{"input":0.12,"output":0.48},"limit":{"output":16384},"attachment":true,"temperature":true,"vision":false},{"id":"openai/gpt-4o-realtime","name":"OpenAI GPT-4o Realtime","display_name":"GPT-4o Realtime","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","audio"],"output":["text","audio"]},"cost":{"input":4,"output":16},"limit":{"output":4096},"attachment":true,"temperature":true,"vision":false},{"id":"openai/gpt-4o-mini-realtime","name":"OpenAI GPT-4o mini Realtime","display_name":"GPT-4o mini Realtime","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","audio"],"output":["text","audio"]},"cost":{"input":0.48,"output":1.92},"limit":{"output":4096},"attachment":true,"temperature":true,"vision":false},{"id":"openai/gpt-image-1","name":"OpenAI GPT Image 1","display_name":"GPT Image 1","type":"imageGeneration","modalities":{"input":["text"],"output":["image"]},"cost":{"input":4,"output":32},"attachment":false,"temperature":true,"reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{}},{"id":"openai/gpt-4o-mini-tts","name":"OpenAI GPT-4o mini TTS","display_name":"GPT-4o mini TTS","type":"audio","modalities":{"input":["text"],"output":["audio"]},"cost":{"input":0.48,"output":0.96},"attachment":false,"temperature":false,"reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{}},{"id":"openai/tts-1-hd","name":"OpenAI TTS-1 HD","display_name":"TTS-1 HD","type":"audio","modalities":{"input":["text"],"output":["audio"]},"cost":{"input":24},"attachment":false,"temperature":false,"reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{}},{"id":"openai/gpt-4o-transcribe","name":"OpenAI GPT-4o Transcribe","display_name":"GPT-4o Transcribe","type":"audio","modalities":{"input":["audio"],"output":["text"]},"cost":{"input":2,"output":8},"limit":{"output":2000},"attachment":false,"temperature":false,"reasoning":{"supported":false},"tool_call":false,"vision":false},{"id":"openai/whisper","name":"OpenAI Whisper","display_name":"Whisper","type":"audio","modalities":{"input":["audio"],"output":["text"]},"cost":{"input":0.0048},"attachment":false,"temperature":false,"reasoning":{"supported":false},"tool_call":false,"vision":false,"limit":{}},{"id":"openai/gpt-4o-search-preview","name":"OpenAI GPT-4o Search Preview","display_name":"GPT-4o Search Preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":2,"output":8},"limit":{"output":16384},"attachment":true,"temperature":true,"vision":false},{"id":"openai/computer-use-preview","name":"OpenAI Computer Use Preview","display_name":"computer-use-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":2.4,"output":9.6},"limit":{"output":1024},"attachment":true,"temperature":true,"vision":false},{"id":"google/gemini-2.5-pro","name":"Google Gemini 2.5 Pro","display_name":"Gemini 2.5 Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1,"output":8},"limit":{"output":65536},"attachment":true,"temperature":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash","name":"Google Gemini 2.5 Flash","display_name":"Gemini 2.5 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.12,"output":0.48},"limit":{"output":65536},"attachment":true,"temperature":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.0-flash","name":"Google Gemini 2.0 Flash","display_name":"Gemini 2.0 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.08,"output":0.32},"limit":{"output":8192},"attachment":true,"temperature":true},{"id":"google/imagen-3","name":"Google Imagen 3","display_name":"Imagen 3","type":"imageGeneration","modalities":{"input":["text"],"output":["image"]},"cost":{"input":0.024},"attachment":false,"temperature":true,"reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{}},{"id":"google/veo-2","name":"Google Veo 2","display_name":"Veo 2","type":"video","modalities":{"input":["text","image"],"output":["video"]},"cost":{"input":0.28},"metadata":{"unit":"per-second"},"attachment":false,"temperature":true,"reasoning":{"supported":false},"tool_call":false,"vision":true,"limit":{}},{"id":"anthropic/claude-sonnet-4","name":"Anthropic Claude Sonnet 4","display_name":"Claude Sonnet 4","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2.4,"output":12},"limit":{"context":200000,"output":200000},"attachment":true,"temperature":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4","name":"Anthropic Claude Opus 4","display_name":"Claude Opus 4","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":12,"output":60},"limit":{"context":200000},"attachment":true,"temperature":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-3.7-sonnet","name":"Anthropic Claude 3.7 Sonnet","display_name":"Claude 3.7 Sonnet","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2.4,"output":12},"limit":{"context":200000,"output":200000},"attachment":true,"temperature":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}}},{"id":"anthropic/claude-3.5-haiku","name":"Anthropic Claude 3.5 Haiku","display_name":"Claude 3.5 Haiku","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"vision":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.64,"output":3.2},"limit":{"context":200000},"attachment":true,"temperature":true},{"id":"xai/grok-3","name":"xAI Grok-3","display_name":"Grok-3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":2.4,"output":12},"limit":{"output":8192},"attachment":true,"temperature":true,"vision":false},{"id":"xai/grok-3-mini","name":"xAI Grok-3 Mini","display_name":"Grok-3 Mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.24,"output":0.4},"limit":{"output":4096},"attachment":true,"temperature":true,"vision":false},{"id":"deepseek/deepseek-r1","name":"DeepSeek Reasoner","display_name":"DeepSeek R1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.1104,"output":1.7632},"limit":{"output":8192},"attachment":true,"temperature":true,"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","display_name":"DeepSeek Chat","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.0552,"output":0.8816},"limit":{"output":8192},"attachment":true,"temperature":true,"vision":false}],"name":"burncloud","display_name":"burncloud"},"cherryin":{"id":"cherryin","models":[{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5","display_name":"Claude Opus 4.5","type":"chat","reasoning":{"supported":true,"default":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"tool_call":true,"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":200000,"output":64000},"metadata":{"pricing":{"cache_read":0.5,"input":5,"output":25},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"agent/deepseek-v3.1-terminus(free)","name":"Agent: DeepSeek-V3.1-Terminus","display_name":"Agent: DeepSeek-V3.1-Terminus","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":160000,"output":32000},"open_weights":false,"type":"chat"},{"id":"agent/deepseek-v3.2-exp(free)","name":"Agent: DeepSeek-V3.2-Exp","display_name":"Agent: DeepSeek-V3.2-Exp","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163000,"output":163000},"open_weights":false,"type":"chat"},{"id":"agent/glm-4.6(free)","name":"Agent: glm-4.6","display_name":"Agent: glm-4.6","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"open_weights":false,"type":"chat"},{"id":"agent/kimi-k2-0905(free)","name":"Agent: Kimi-K2-0905","display_name":"Agent: Kimi-K2-0905","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"type":"chat"},{"id":"agent/kimi-k2-thinking(free)","name":"Agent: kimi-k2-thinking","display_name":"Agent: kimi-k2-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"agent/minimax-m2(free)","name":"Agent: minimax-m2","display_name":"Agent: minimax-m2","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":192000},"open_weights":false,"type":"chat"},{"id":"agent/qwen3-coder-30b-a3b-instruct(free)","name":"Agent: qwen3-coder-30b-a3b-instruct","display_name":"Agent: qwen3-coder-30b-a3b-instruct","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":2000000,"output":262000},"open_weights":false,"type":"chat"},{"id":"agent/qwen3-coder-480b-a35b-instruct(free)","name":"Agent: qwen3-coder-480b-a35b-instruct","display_name":"Agent: qwen3-coder-480b-a35b-instruct","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262000,"output":262000},"open_weights":false,"type":"chat"},{"id":"agent/qwen3-next-80b-a3b-instruct(free)","name":"Agent: qwen3-next-80b-a3b-instruct","display_name":"Agent: qwen3-next-80b-a3b-instruct","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":256000,"output":256000},"open_weights":false,"type":"chat"},{"id":"agent/qwen3-next-80b-a3b-thinking(free)","name":"Agent: qwen3-next-80b-a3b-thinking","display_name":"Agent: qwen3-next-80b-a3b-thinking","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":256000,"output":256000},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"anthropic/claude-3.7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2024-01","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"display_name":"Anthropic: Claude 3.7 Sonnet","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":false,"summaries":false,"visibility":"full","continuation":["thinking_blocks"],"notes":["Anthropic uses thinking budget tokens"]}},"type":"chat"},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: claude-haiku-4-5","display_name":"Anthropic: claude-haiku-4-5","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":204800,"output":131072},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}},"type":"chat"},{"id":"anthropic/claude-opus-4","name":"Anthropic: Claude Opus 4","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"display_name":"Anthropic: Claude Opus 4","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}},"type":"chat"},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"display_name":"Anthropic: Claude Opus 4.1","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}},"type":"chat"},{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"display_name":"Anthropic: Claude Sonnet 4","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}},"type":"chat"},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"display_name":"Anthropic: Claude Sonnet 4.5","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}},"type":"chat"},{"id":"BAAI/bge-reranker-v2-m3(free)","name":"BAAI/bge-reranker-v2-m3","display_name":"BAAI/bge-reranker-v2-m3","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{},"open_weights":false,"type":"rerank"},{"id":"bytedance/seed-oss-36b-instruct","name":"ByteDance: Seed OSS 36B Instruct","display_name":"ByteDance: Seed OSS 36B Instruct","type":"completion","reasoning":{"supported":true},"tool_call":false,"metadata":{"source":"public-provider-conf"},"vision":false,"limit":{"context":4096,"output":4096},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-ocr(free)","name":"DeepSeek-OCR","display_name":"DeepSeek-OCR","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":8000},"open_weights":false,"type":"chat"},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","display_name":"DeepSeek: R1 0528","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":163840},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2024-07","release_date":"2025-08-20","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"display_name":"DeepSeek V3.1","type":"chat"},{"id":"deepseek/deepseek-v3.1-fast","name":"DeepSeek: DeepSeek V3.1 (free)","display_name":"DeepSeek: DeepSeek V3.1 (free)","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163800},"type":"chat"},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-07","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"display_name":"DeepSeek: DeepSeek V3.1 Terminus","type":"chat"},{"id":"deepseek/deepseek-v3.1-terminus(free)","name":"DeepSeek-V3.1-Terminus","display_name":"DeepSeek-V3.1-Terminus","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":160000,"output":32000},"open_weights":false,"type":"chat"},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","display_name":"DeepSeek: DeepSeek V3.2 Exp","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840},"type":"chat"},{"id":"deepseek/deepseek-v3.2-exp(free)","name":"DeepSeek-V3.2-Exp","display_name":"DeepSeek-V3.2-Exp","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163000,"output":163000},"open_weights":false,"type":"chat"},{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-01","release_date":"2025-07-17","last_updated":"2025-07-17","modalities":{"input":["image","text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"display_name":"Google: Gemini 2.5 Flash","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"google/gemini-2.5-flash-image","name":"Google: Gemini 2.5 Flash Image (Nano Banana)","display_name":"Google: Gemini 2.5 Flash Image (Nano Banana)","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":32768,"output":8192},"type":"image-generation"},{"id":"google/gemini-2.5-flash-image-preview","name":"Google: Gemini 2.5 Flash Image Preview (Nano Banana)","display_name":"Google: Gemini 2.5 Flash Image Preview (Nano Banana)","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":32768,"output":8192},"type":"image-generation"},{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","display_name":"Google: Gemini 2.5 Flash Lite","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"modalities":{"input":["image","text","audio"],"output":["text"]},"limit":{"context":1048576,"output":65535},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["image","text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"display_name":"Google: Gemini 2.5 Pro","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"google/gemini-3-pro-preview","name":"Google: Gemini 3 Pro Preview","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-10","release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["image","text","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"display_name":"Google: Gemini 3 Pro Preview","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}},"type":"chat"},{"id":"inclusionai/ling-1t","name":"inclusionAI: Ling-1T","display_name":"inclusionAI: Ling-1T","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":131072},"type":"chat"},{"id":"meituan/longcat-flash-chat","name":"Meituan: LongCat-Flash-Chat","display_name":"Meituan: LongCat-Flash-Chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"type":"chat"},{"id":"minimax/minimax-m2","name":"MiniMax: minimax-m2","display_name":"MiniMax: minimax-m2","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":192000},"open_weights":false,"type":"chat"},{"id":"minimax/MiniMax-M2(free)","name":"MiniMax: minimax-m2","display_name":"MiniMax: minimax-m2","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":192000},"open_weights":false,"type":"chat"},{"id":"minimaxai/minimax-m1-80k","name":"MiniMax: MiniMax M1","display_name":"MiniMax: MiniMax M1","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":40000},"type":"chat"},{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"display_name":"MoonshotAI: Kimi K2 0905","type":"chat"},{"id":"moonshotai/kimi-k2-0905(free)","name":"MoonshotAI: Kimi-K2-0905","display_name":"MoonshotAI: Kimi-K2-0905","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"type":"chat"},{"id":"moonshotai/kimi-k2-thinking","name":"MoonshotAI: kimi-k2-thinking","display_name":"MoonshotAI: kimi-k2-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"moonshotai/kimi-k2-thinking-turbo","name":"MoonshotAI: kimi-k2-thinking","display_name":"MoonshotAI: kimi-k2-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"type":"chat"},{"id":"moonshotai/kimi-k2-thinking(free)","name":"MoonshotAI: kimi-k2-thinking","display_name":"MoonshotAI: kimi-k2-thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"display_name":"OpenAI: GPT-4.1","type":"chat"},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"display_name":"OpenAI: GPT-4.1 Mini","type":"chat"},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","display_name":"OpenAI: GPT-4.1 Nano","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1047576,"output":32768},"type":"chat"},{"id":"openai/gpt-4o","name":"OpenAI: gpt-4o","display_name":"OpenAI: gpt-4o","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"open_weights":false,"type":"chat"},{"id":"openai/gpt-4o-mini","name":"OpenAI: gpt-4o-mini","display_name":"OpenAI: gpt-4o-mini","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"open_weights":false,"type":"chat"},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"display_name":"OpenAI: GPT-5","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/gpt-5-chat","name":"OpenAI: GPT-5 Chat","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"display_name":"OpenAI: GPT-5 Chat","type":"chat"},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"display_name":"OpenAI: GPT-5 Mini","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"display_name":"OpenAI: GPT-5 Nano","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/gpt-5.1","name":"OpenAI: gpt-5.1","display_name":"OpenAI: gpt-5.1","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/gpt-5.2","name":"OpenAI: gpt-5.2","display_name":"OpenAI: gpt-5.2","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/gpt-5.1-chat","name":"OpenAI: gpt-5.1","display_name":"OpenAI: gpt-5.1","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"open_weights":false,"type":"chat"},{"id":"openai/gpt-image-1","name":"OpenAI: gpt-image-1","display_name":"OpenAI: gpt-image-1","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{},"open_weights":false,"type":"image-generation"},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"display_name":"OpenAI: gpt-oss-120b","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"display_name":"OpenAI: gpt-oss-20b","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"openai/o1","name":"OpenAI: o1","display_name":"OpenAI: o1","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":100000},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/o1-mini","name":"OpenAI: o1-mini","display_name":"OpenAI: o1-mini","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":65536},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/o3","name":"OpenAI: o3","display_name":"OpenAI: o3","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":100000},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2024-06","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"display_name":"OpenAI: o4 Mini","extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}},"type":"chat"},{"id":"qwen/qwen-image-edit-2509(free)","name":"Qwen: qwen-image-edit","display_name":"Qwen: qwen-image-edit","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{},"open_weights":false,"type":"chat"},{"id":"qwen/qwen-image-edit(free)","name":"Qwen: qwen-image-edit","display_name":"Qwen: qwen-image-edit","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{},"open_weights":false,"type":"chat"},{"id":"qwen/qwen-image(free)","name":"Qwen: qwen-image","display_name":"Qwen: qwen-image","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{},"open_weights":false,"type":"chat"},{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","display_name":"Qwen: Qwen3 235B A22B Instruct 2507","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"type":"chat"},{"id":"qwen/qwen3-235b-a22b-instruct-2507(free)","name":"Qwen: qwen3-235b-a22b-instruct-2507","display_name":"Qwen: qwen3-235b-a22b-instruct-2507","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"type":"chat"},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-04","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"display_name":"Qwen: Qwen3 235B A22B Thinking 2507","extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-235b-a22b-thinking-2507(free)","name":"Qwen: qwen3-235b-a22b-thinking-2507","display_name":"Qwen: qwen3-235b-a22b-thinking-2507","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":262144},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"knowledge":"2025-04","release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"display_name":"Qwen: Qwen3 30B A3B Instruct 2507","type":"chat"},{"id":"qwen/qwen3-30b-a3b-instruct-2507(free)","name":"Qwen: qwen3-30b-a3b-instruct-2507","display_name":"Qwen: qwen3-30b-a3b-instruct-2507","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"type":"chat"},{"id":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","display_name":"Qwen: Qwen3 30B A3B Thinking 2507","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-30b-a3b-thinking-2507(free)","name":"Qwen: qwen3-30b-a3b-thinking-2507","display_name":"Qwen: qwen3-30b-a3b-thinking-2507","attachment":false,"reasoning":{"supported":true},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-8b","name":"Qwen: Qwen3 8B","display_name":"Qwen: Qwen3 8B","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":20000},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-8b(free)","name":"Qwen: qwen3-8b","display_name":"Qwen: qwen3-8b","attachment":false,"reasoning":{"supported":true},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"display_name":"Qwen: Qwen3 Coder 480B A35B","type":"chat"},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","display_name":"Qwen: Qwen3 Coder 30B A3B Instruct","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":262144},"type":"chat"},{"id":"qwen/qwen3-coder-30b-a3b-instruct(free)","name":"Qwen: qwen3-coder-30b-a3b-instruct","display_name":"Qwen: qwen3-coder-30b-a3b-instruct","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":2000000,"output":262000},"open_weights":false,"type":"chat"},{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen: Qwen3 Coder 480B A35B Instruct","display_name":"Qwen: Qwen3 Coder 480B A35B Instruct","type":"completion","reasoning":{"supported":false},"tool_call":false,"metadata":{"source":"public-provider-conf"},"vision":false,"limit":{"context":4096,"output":4096}},{"id":"qwen/qwen3-coder-480b-a35b-instruct(free)","name":"Qwen: qwen3-coder-480b-a35b-instruct","display_name":"Qwen: qwen3-coder-480b-a35b-instruct","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262000,"output":262000},"open_weights":false,"type":"chat"},{"id":"qwen/qwen3-embedding-0.6b","name":"qwen/qwen3-embedding-0.6b","display_name":"qwen/qwen3-embedding-0.6b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"metadata":{"developer":"Qwen","developerId":13,"providerId":15,"modelRatio":0.034,"cacheRatio":1,"completionRatio":1,"order":600,"flag":0,"modalities":["text"],"typeHints":["embedding"],"source":"public-provider-conf"},"vision":false,"limit":{"context":8192,"output":8192}},{"id":"qwen/qwen3-embedding-0.6b(free)","name":"Qwen: qwen3-embedding-0.6b","display_name":"Qwen: qwen3-embedding-0.6b","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"type":"embedding"},{"id":"qwen/qwen3-embedding-4b","name":"qwen/qwen3-embedding-4b","display_name":"qwen/qwen3-embedding-4b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"metadata":{"developer":"Qwen","developerId":13,"providerId":15,"modelRatio":0.034,"cacheRatio":1,"completionRatio":1,"order":600,"flag":0,"modalities":["text"],"typeHints":["embedding"],"source":"public-provider-conf"},"vision":false,"limit":{"context":8192,"output":8192}},{"id":"qwen/qwen3-embedding-4b(free)","name":"Qwen: qwen3-embedding-4b","display_name":"Qwen: qwen3-embedding-4b","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"type":"embedding"},{"id":"qwen/qwen3-embedding-8b","name":"qwen/qwen3-embedding-8b","display_name":"qwen/qwen3-embedding-8b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"metadata":{"developer":"Qwen","developerId":13,"providerId":15,"modelRatio":0.034,"cacheRatio":1,"completionRatio":1,"order":600,"flag":0,"modalities":["text"],"typeHints":["embedding"],"source":"public-provider-conf"},"vision":false,"limit":{"context":8192,"output":8192}},{"id":"qwen/qwen3-embedding-8b(free)","name":"Qwen: qwen3-embedding-8b","display_name":"Qwen: qwen3-embedding-8b","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"type":"embedding"},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"knowledge":"2025-04","release_date":"2025-09-11","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"display_name":"Qwen: Qwen3 Next 80B A3B Instruct","type":"chat"},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","display_name":"Qwen: Qwen3 Next 80B A3B Thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-omni-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","display_name":"Qwen: Qwen3 VL 30B A3B Instruct","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":262144},"type":"chat"},{"id":"qwen/qwen3-omni-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","display_name":"Qwen: Qwen3 VL 30B A3B Thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":262144},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-reranker-0.6b","name":"qwen/qwen3-reranker-0.6b","display_name":"qwen/qwen3-reranker-0.6b","type":"rerank","reasoning":{"supported":false},"tool_call":false,"metadata":{"developer":"Qwen","developerId":13,"providerId":15,"modelRatio":0.5,"cacheRatio":1,"completionRatio":1,"order":100,"flag":0,"source":"public-provider-conf"},"vision":false,"limit":{"context":8192,"output":8192}},{"id":"qwen/qwen3-reranker-0.6b(free)","name":"Qwen: qwen3-reranker-0.6b","display_name":"Qwen: qwen3-reranker-0.6b","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":16000,"output":8000},"open_weights":false,"type":"rerank"},{"id":"qwen/qwen3-reranker-4b","name":"qwen/qwen3-reranker-4b","display_name":"qwen/qwen3-reranker-4b","type":"rerank","reasoning":{"supported":false},"tool_call":false,"metadata":{"developer":"Qwen","developerId":13,"providerId":15,"modelRatio":0.5,"cacheRatio":1,"completionRatio":1,"order":100,"flag":0,"source":"public-provider-conf"},"vision":false,"limit":{"context":8192,"output":8192}},{"id":"qwen/qwen3-reranker-4b(free)","name":"Qwen: qwen3-reranker-4b","display_name":"Qwen: qwen3-reranker-4b","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{},"open_weights":false,"type":"rerank"},{"id":"qwen/qwen3-reranker-8b","name":"qwen/qwen3-reranker-8b","display_name":"qwen/qwen3-reranker-8b","type":"rerank","reasoning":{"supported":false},"tool_call":false,"metadata":{"developer":"Qwen","developerId":13,"providerId":15,"modelRatio":0.5,"cacheRatio":1,"completionRatio":1,"order":100,"flag":0,"source":"public-provider-conf"},"vision":false,"limit":{"context":8192,"output":8192}},{"id":"qwen/qwen3-reranker-8b(free)","name":"Qwen: qwen3-reranker-8b","display_name":"Qwen: qwen3-reranker-8b","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{},"open_weights":false,"type":"rerank"},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","display_name":"Qwen: Qwen3 VL 235B A22B Instruct","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072},"type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-instruct(free)","name":"Qwen: qwen3-vl-235b-a22b-instruct","display_name":"Qwen: qwen3-vl-235b-a22b-instruct","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":131000,"output":33000},"open_weights":false,"type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","display_name":"Qwen: Qwen3 VL 235B A22B Thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":65536,"output":65536},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-vl-235b-a22b-thinking(free)","name":"Qwen: qwen3-vl-235b-a22b-thinking","display_name":"Qwen: qwen3-vl-235b-a22b-thinking","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":131000,"output":33000},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","display_name":"Qwen: Qwen3 VL 30B A3B Instruct","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":262144},"type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-instruct(free)","name":"Qwen: qwen3-vl-30b-a3b-instruct","display_name":"Qwen: qwen3-vl-30b-a3b-instruct","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":128000,"output":32000},"open_weights":false,"type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","display_name":"Qwen: Qwen3 VL 30B A3B Thinking","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":262144},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"qwen/qwen3-vl-30b-a3b-thinking(free)","name":"Qwen: qwen3-vl-30b-a3b-thinking","display_name":"Qwen: qwen3-vl-30b-a3b-thinking","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":128000,"output":32000},"open_weights":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}},"type":"chat"},{"id":"tencent/hunyuan-mt-7b","name":"Tencent: Hunyuan A13B Instruct","display_name":"Tencent: Hunyuan A13B Instruct","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768},"type":"chat"},{"id":"tencent/hunyuan-mt-7b(free)","name":"Tencent: tencent/Hunyuan-MT-7B","display_name":"Tencent: tencent/Hunyuan-MT-7B","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{},"open_weights":false,"type":"chat"},{"id":"x-ai/grok-2-image","name":"grok-2","display_name":"grok-2","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text","image"]},"metadata":{"developer":"Grok","developerId":9,"providerId":46,"modelRatio":0.9,"cacheRatio":1,"completionRatio":5,"order":0,"flag":0,"tags":["multi_modal"],"modalities":["text","image"],"typeHints":["t2t"],"source":"public-provider-conf"},"vision":true,"limit":{"context":8192,"output":8192}},{"id":"x-ai/grok-3","name":"xAI: Grok 3","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"knowledge":"2024-11","release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"display_name":"xAI: Grok 3","type":"chat"},{"id":"x-ai/grok-3-mini","name":"xAI: Grok 3 Mini","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2024-11","release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"display_name":"xAI: Grok 3 Mini","type":"chat"},{"id":"x-ai/grok-4","name":"xAI: Grok 4","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-07","release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"display_name":"xAI: Grok 4","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"x-ai/grok-4-fast-non-reasoning","name":"x-ai/grok-4-fast-non-reasoning","display_name":"x-ai/grok-4-fast-non-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":false,"metadata":{"developer":"Grok","developerId":9,"providerId":29,"modelRatio":0.1,"cacheRatio":0.25,"completionRatio":2.5,"order":800,"flag":1,"billingConfig":"{\n  \"model_name\": \"grok-4-fast-non-reasoning\",\n  \"default_tier\": \"tier1\",\n  \"token_based_tier_configs\": {\n    \"tier1\": {\n      \"tier_condition\": {\n        \"min_tokens\": 0,\n        \"max_tokens\": 128000\n      },\n      \"model_ratio\": 0.1,\n      \"prompt_tokens_ratio\": 1.0,\n      \"completion_tokens_ratio\": 2.5,\n      \"cached_tokens_ratio\": 0.25\n    },\n    \"tier2\": {\n      \"tier_condition\": {\n        \"min_tokens\": 128001,\n        \"max_tokens\": -1\n      },\n      \"model_ratio\": 0.2,\n      \"prompt_tokens_ratio\": 1.0,\n      \"completion_tokens_ratio\": 2.5,\n      \"cached_tokens_ratio\": 0.125\n    }\n  },\n  \"enabled_billing_items\": [\n    \"prompt_tokens\",\n    \"completion_tokens\",\n    \"cached_tokens\"\n  ]\n}","source":"public-provider-conf"},"vision":false,"limit":{"context":2000000,"output":2000000}},{"id":"x-ai/grok-4-fast-reasoning","name":"x-ai/grok-4-fast-reasoning","display_name":"x-ai/grok-4-fast-reasoning","type":"chat","reasoning":{"supported":true},"tool_call":false,"metadata":{"developer":"Grok","developerId":9,"providerId":29,"modelRatio":0.1,"cacheRatio":0.25,"completionRatio":2.5,"order":800,"flag":1,"billingConfig":"{\n  \"model_name\": \"grok-4-fast-reasoning\",\n  \"default_tier\": \"tier1\",\n  \"token_based_tier_configs\": {\n    \"tier1\": {\n      \"tier_condition\": {\n        \"min_tokens\": 0,\n        \"max_tokens\": 128000\n      },\n      \"model_ratio\": 0.1,\n      \"prompt_tokens_ratio\": 1.0,\n      \"completion_tokens_ratio\": 2.5,\n      \"cached_tokens_ratio\": 0.25\n    },\n    \"tier2\": {\n      \"tier_condition\": {\n        \"min_tokens\": 128001,\n        \"max_tokens\": -1\n      },\n      \"model_ratio\": 0.2,\n      \"prompt_tokens_ratio\": 1.0,\n      \"completion_tokens_ratio\": 2.5,\n      \"cached_tokens_ratio\": 0.125\n    }\n  },\n  \"enabled_billing_items\": [\n    \"prompt_tokens\",\n    \"completion_tokens\",\n    \"cached_tokens\"\n  ]\n}","source":"public-provider-conf"},"vision":false,"limit":{"context":2000000,"output":2000000},"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-code-fast-1","name":"xAI: Grok Code Fast 1","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-08","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":10000},"display_name":"xAI: Grok Code Fast 1","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"z-ai/glm-4.5","name":"Z.AI: GLM 4.5","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"display_name":"Z.AI: GLM 4.5","type":"chat"},{"id":"z-ai/glm-4.5-flash","name":"z-ai/glm-4.5-flash","display_name":"z-ai/glm-4.5-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"metadata":{"developer":"ChatGLM","developerId":5,"providerId":8,"modelRatio":0.01,"cacheRatio":1,"completionRatio":1,"order":1,"flag":0,"modalities":["text"],"source":"public-provider-conf"},"vision":false,"limit":{"context":8192,"output":8192}},{"id":"z-ai/glm-4.5(free)","name":"Z.AI: glm-4.5","display_name":"Z.AI: glm-4.5","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":98304},"open_weights":false,"type":"chat"},{"id":"z-ai/glm-4.5v","name":"Z.AI: GLM 4.5V","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"display_name":"Z.AI: GLM 4.5V","type":"chat"},{"id":"z-ai/glm-4.5v(free)","name":"Z.AI: glm-4.5v","display_name":"Z.AI: glm-4.5v","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":64000,"output":16384},"open_weights":false,"type":"chat"},{"id":"z-ai/glm-4.6","name":"Z.AI: GLM 4.6","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-09","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"display_name":"Z.AI: GLM 4.6","extra_capabilities":{"reasoning":{"supported":true}},"type":"chat"},{"id":"z-ai/glm-4.6(free)","name":"Z.AI: glm-4.6","display_name":"Z.AI: glm-4.6","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"open_weights":false,"type":"chat"},{"id":"z-ai/glm-4.7","name":"Z.AI: GLM 4.7","display_name":"Z.AI: GLM 4.7","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"cost":{"input":0.273974,"output":1.095896,"cache_read":0.054795},"modalities":{"input":["text"],"output":["text"]},"limit":{"context":200000,"output":200000},"open_weights":true,"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.054795,"input":0.273974,"output":1.095896},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomi/mimo-v2-flash","name":"Xiaomi: Mimo V2 Flash","display_name":"Xiaomi: Mimo V2 Flash","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"cost":{"input":0.1918,"output":0.5754,"cache_read":0.03836},"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"open_weights":false,"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.03836,"input":0.1918,"output":0.5754},"source":"public-provider-conf"},"vision":false},{"id":"xiaomimimo/mimo-v2-flash","name":"Xiaomi: Mimo V2 Flash","display_name":"Xiaomi: Mimo V2 Flash","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"cost":{"input":0.1918,"output":0.5754,"cache_read":0.03836},"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"open_weights":false,"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.03836,"input":0.1918,"output":0.5754},"source":"public-provider-conf"},"vision":false},{"id":"minimax/minimax-m2.1","name":"MiniMax: minimax-m2.1","display_name":"MiniMax: minimax-m2.1","type":"chat","attachment":false,"reasoning":{"supported":true},"temperature":true,"tool_call":false,"cost":{"input":0.288,"output":1.152},"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":204800},"open_weights":false,"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.288,"output":1.152},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax: minimax-m2.1-lightning","display_name":"MiniMax: minimax-m2.1-lightning","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"cost":{"input":0.144,"output":0.576},"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":204800},"open_weights":false,"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.144,"output":0.576},"source":"public-provider-conf"},"vision":false}],"name":"cherryin","display_name":"cherryin"},"doubao":{"id":"doubao","name":"Doubao","display_name":"Doubao","doc":"https://www.volcengine.com/docs/82379/1330310?lang=zh","updated_at":"2026-10-18T12:21:35Z","metadata":{"source":"volcengine-docs","doc_detail_url":"https://www.volcengine.com/api/doc/getDocDetail?LibraryID=82379&DocumentID=1330310&lang=zh"},"models":[{"id":"deepseek-v4-1-flash-260910","name":"deepseek-v4-1-flash-260910","display_name":"deepseek-v4-1-flash-260910","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1024000,"output":384000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":384000,"max_input_tokens":1024000,"canonical_id":"deepseek-v4-1-flash","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?name=deepseek-v4-1-flash","section_titles":["上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 384k 最大思维链: 384k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"deepseek-v4-1-flash-261017","name":"deepseek-v4-1-flash-261017","display_name":"deepseek-v4-1-flash-261017","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1024000,"output":384000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":384000,"max_input_tokens":1024000,"canonical_id":"deepseek-v4-1-flash","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?name=deepseek-v4-1-flash","section_titles":["上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 384k 最大思维链: 384k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"deepseek-v4-flash-ga-260731","name":"deepseek-v4-flash-ga-260731","display_name":"deepseek-v4-flash-ga-260731","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1024000,"output":384000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":1024000,"canonical_id":"deepseek-v4-flash-ga","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?name=deepseek-v4-flash-ga","section_titles":["上下文缓存能力","工具调用能力","文本生成能力"],"capabilities":["工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 384k 最大思维链: 128k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"deepseek-v4-pro-260425","name":"deepseek-v4-pro-260425","display_name":"deepseek-v4-pro-260425","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1024000,"output":384000,"requests_per_minute":15000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":1024000,"canonical_id":"deepseek-v4-pro","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=deepseek-v4-pro","section_titles":["上下文缓存能力","工具调用能力","文本生成能力"],"capabilities":["工具调用","文本生成","深度思考"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 384k 最大思维链: 128k","最大 RPM: 15000 最大 TPM: 1500000"],"features":["context-cache"]}},{"id":"deepseek-v4-pro-ga-260813","name":"deepseek-v4-pro-ga-260813","display_name":"deepseek-v4-pro-ga-260813","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1024000,"output":384000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":1024000,"canonical_id":"deepseek-v4-pro-ga","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?name=deepseek-v4-pro-ga","section_titles":["上下文缓存能力","工具调用能力","文本生成能力"],"capabilities":["工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 384k 最大思维链: 128k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"doubao-embedding-vision-250615","name":"doubao-embedding-vision-250615","display_name":"doubao-embedding-vision-250615","type":"embedding","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text","video"],"output":["embedding"]},"limit":{"context":128000,"requests_per_minute":15000},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-embedding-vision","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-embedding-vision","section_titles":["向量化能力"],"capabilities":["多模态向量化"],"raw_limits":["最大 RPM: 15000 最大 TPM: 1200000"]}},{"id":"doubao-embedding-vision-251215","name":"doubao-embedding-vision-251215","display_name":"doubao-embedding-vision-251215","type":"embedding","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text","video"],"output":["embedding"]},"limit":{"context":128000,"requests_per_minute":15000},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-embedding-vision","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-embedding-vision","section_titles":["向量化能力"],"capabilities":["多模态向量化"],"raw_limits":["最大 RPM: 15000 最大 TPM: 1200000"]}},{"id":"doubao-seed-2-0-code-preview-260215","name":"doubao-seed-2-0-code-preview-260215","display_name":"doubao-seed-2-0-code-preview-260215","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":128000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":224000,"canonical_id":"doubao-seed-2-0-code","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-0-code","section_titles":["上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","视觉定位"],"raw_limits":["上下文窗口: 256k 最大输入: 224k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-0-lite-260215","name":"doubao-seed-2-0-lite-260215","display_name":"doubao-seed-2-0-lite-260215","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":128000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":224000,"canonical_id":"doubao-seed-2-0-lite","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-0-lite","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出","视觉定位"],"raw_limits":["上下文窗口: 256k 最大输入: 224k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-0-lite-260428","name":"doubao-seed-2-0-lite-260428","display_name":"doubao-seed-2-0-lite-260428","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":128000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":224000,"canonical_id":"doubao-seed-2-0-lite","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-0-lite","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 256k 最大输入: 224k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-0-mini-260215","name":"doubao-seed-2-0-mini-260215","display_name":"doubao-seed-2-0-mini-260215","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":128000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":224000,"canonical_id":"doubao-seed-2-0-mini","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-0-mini","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出","视觉定位"],"raw_limits":["上下文窗口: 256k 最大输入: 224k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-0-mini-260428","name":"doubao-seed-2-0-mini-260428","display_name":"doubao-seed-2-0-mini-260428","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":128000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":224000,"canonical_id":"doubao-seed-2-0-mini","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-0-mini","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 256k 最大输入: 224k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-0-pro-260215","name":"doubao-seed-2-0-pro-260215","display_name":"doubao-seed-2-0-pro-260215","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":128000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":224000,"canonical_id":"doubao-seed-2-0-pro","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-0-pro","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出","视觉定位"],"raw_limits":["上下文窗口: 256k 最大输入: 224k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-1-lite-260915","name":"doubao-seed-2-1-lite-260915","display_name":"doubao-seed-2-1-lite-260915","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1024000,"output":256000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":256000,"max_input_tokens":1024000,"canonical_id":"doubao-seed-2-1-lite","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-1-lite","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 256k 最大思维链: 256k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-1-pro-260628","name":"doubao-seed-2-1-pro-260628","display_name":"doubao-seed-2-1-pro-260628","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":256000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":256000,"max_input_tokens":256000,"canonical_id":"doubao-seed-2-1-pro","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-1-pro","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 256k 最大输入: 256k 最大回答(默认 4k): 256k 最大思维链: 256k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-1-pro-260915","name":"doubao-seed-2-1-pro-260915","display_name":"doubao-seed-2-1-pro-260915","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1024000,"output":256000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":256000,"max_input_tokens":1024000,"canonical_id":"doubao-seed-2-1-pro","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-1-pro","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 256k 最大思维链: 256k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"doubao-seed-2-1-turbo-260628","name":"doubao-seed-2-1-turbo-260628","display_name":"doubao-seed-2-1-turbo-260628","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":256000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":256000,"max_input_tokens":256000,"canonical_id":"doubao-seed-2-1-turbo","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-2-1-turbo","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 256k 最大输入: 256k 最大回答(默认 4k): 256k 最大思维链: 256k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"doubao-seed-character-251128","name":"doubao-seed-character-251128","display_name":"doubao-seed-character-251128","type":"chat","attachment":false,"reasoning":{"supported":false},"tool_call":true,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":32000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_input_tokens":96000,"canonical_id":"doubao-seed-character","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-character","section_titles":["上下文缓存能力","工具调用能力","文本生成能力"],"capabilities":["工具调用","文本生成"],"raw_limits":["上下文窗口: 128k 最大输入: 96k 最大回答(默认 4k): 32k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-character-260628","name":"doubao-seed-character-260628","display_name":"doubao-seed-character-260628","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":128000,"output":32000,"requests_per_minute":30000},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":96000,"canonical_id":"doubao-seed-character","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-character&_vtm_=a106466.b106468.0_0.0_0.0.1961_7630866813484467762&projectName=default","section_titles":["上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 128k 最大输入: 96k 最大回答(默认 4k): 32k 最大思维链: 128k","最大 RPM: 30000 最大 TPM: 5000000"],"features":["context-cache"]}},{"id":"doubao-seed-evolving","name":"doubao-seed-evolving","display_name":"doubao-seed-evolving","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1024000,"output":256000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":256000,"max_input_tokens":1024000,"canonical_id":"doubao-seed-evolving","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-evolving","section_titles":["GUI 任务处理能力","上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考","结构化输出"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 256k 最大思维链: 256k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"doubao-seed-translation-250915","name":"doubao-seed-translation-250915","display_name":"doubao-seed-translation-250915","type":"chat","attachment":false,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":4000,"output":3000,"requests_per_minute":5000},"metadata":{"source":"volcengine-docs","max_input_tokens":1000,"canonical_id":"doubao-seed-translation","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-translation","section_titles":["文本生成能力"],"capabilities":["文本生成"],"raw_limits":["上下文窗口: 4k 最大输入: 1k 最大回答(默认 3k): 3k 最大思维链: -","最大 RPM: 5000 500000 TPM"]}},{"id":"doubao-seedance-1-0-pro-250528","name":"doubao-seedance-1-0-pro-250528","display_name":"doubao-seedance-1-0-pro-250528","type":"video","attachment":false,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["video"]},"limit":{"requests_per_minute":600,"requests_per_day":500000000000},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedance-1-0-pro","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedance-1-0-pro&projectName=default","section_titles":["视频生成能力"],"capabilities":["文生视频"],"raw_limits":["最大 RPM: 600 最大并发: 10","最大 TPD: 5000亿"]}},{"id":"doubao-seedance-1-0-pro-fast-251015","name":"doubao-seedance-1-0-pro-fast-251015","display_name":"doubao-seedance-1-0-pro-fast-251015","type":"video","attachment":false,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["video"]},"limit":{"requests_per_minute":600,"requests_per_day":500000000000},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedance-1-0-pro-fast","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedance-1-0-pro-fast&projectName=default","section_titles":["视频生成能力"],"capabilities":["文生视频"],"raw_limits":["最大 RPM: 600 最大并发: 10","最大 TPD: 5000亿"]}},{"id":"doubao-seedance-2-0-260128","name":"doubao-seedance-2-0-260128","display_name":"doubao-seedance-2-0-260128","type":"video","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["text","video"],"output":["video"]},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedance-2-0","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedance-2-0&projectName=default","section_titles":["视频生成能力"],"capabilities":["文生视频","编辑视频"],"raw_limits":["非 4k 分辨率： 最大 RPM: 企业用户: 600 个人用户: 180 最大并发: 企业用户: 10 个人用户: 3 个人用户: 3 4k 分辨率： 最大 RPM 企业用户：15 个人用户：15 最大并发 企业用户：1 个人用户：1"]}},{"id":"doubao-seedance-2-0-fast-260128","name":"doubao-seedance-2-0-fast-260128","display_name":"doubao-seedance-2-0-fast-260128","type":"video","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["text","video"],"output":["video"]},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedance-2-0-fast","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedance-2-0-fast","section_titles":["视频生成能力"],"capabilities":["文生视频","编辑视频"],"raw_limits":["最大 RPM: 企业用户: 600 个人用户: 180 最大并发: 企业用户: 10 个人用户: 3"]}},{"id":"doubao-seedance-2-0-mini-260615","name":"doubao-seedance-2-0-mini-260615","display_name":"doubao-seedance-2-0-mini-260615","type":"video","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["text","video"],"output":["video"]},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedance-2-0-mini","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedance-2-0-mini","section_titles":["视频生成能力"],"capabilities":["文生视频","编辑视频"],"raw_limits":["最大 RPM: 企业用户: 600 个人用户: 180 最大并发: 企业用户: 10 个人用户: 3"]}},{"id":"doubao-seedance-2-5-260628","name":"doubao-seedance-2-5-260628","display_name":"doubao-seedance-2-5-260628","type":"video","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["text","video"],"output":["video"]},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedance-2-5","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedance-2-5","section_titles":["视频生成能力"],"capabilities":["文生视频","编辑视频"],"raw_limits":["最大 RPM: 企业用户: 600 个人用户: 180 最大并发: 企业用户: 10 个人用户: 3"]}},{"id":"doubao-seedream-4-0-250828","name":"doubao-seedream-4-0-250828","display_name":"doubao-seedream-4-0-250828","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["image"]},"limit":{"requests_per_minute":500},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedream-4-0","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedream-4-0","section_titles":["图片生成能力"],"capabilities":["图生图","文生图"]}},{"id":"doubao-seedream-4-5-251128","name":"doubao-seedream-4-5-251128","display_name":"doubao-seedream-4-5-251128","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["image"]},"limit":{"requests_per_minute":500},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedream-4-5","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedream-4-5","section_titles":["图片生成能力"],"capabilities":["图生图","文生图"]}},{"id":"doubao-seedream-5-0-260128","name":"doubao-seedream-5-0-260128","display_name":"doubao-seedream-5-0-260128","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["image"]},"limit":{"requests_per_minute":500},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedream-5-0","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedream-5-0","section_titles":["图片生成能力"],"capabilities":["图生图","文生图"]}},{"id":"doubao-seedream-5-0-flash-260915","name":"doubao-seedream-5-0-flash-260915","display_name":"doubao-seedream-5-0-flash-260915","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["image"]},"limit":{"requests_per_minute":500},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedream-5-0-flash","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedream-5-0-flash","section_titles":["图片生成能力"],"capabilities":["图生图","文生图"]}},{"id":"doubao-seedream-5-0-pro-260628","name":"doubao-seedream-5-0-pro-260628","display_name":"doubao-seedream-5-0-pro-260628","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["image"]},"limit":{"requests_per_minute":500},"metadata":{"source":"volcengine-docs","canonical_id":"doubao-seedream-5-0-pro","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedream-5-0-pro","section_titles":["图片生成能力"],"capabilities":["图生图","文生图"]}},{"id":"glm-5-2-260617","name":"glm-5-2-260617","display_name":"glm-5-2-260617","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"last_updated":"2026-10-18T12:21:35Z","vision":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1024000,"output":128000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":1024000,"canonical_id":"glm-5-2","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?Id=glm-5-2","section_titles":["上下文缓存能力","工具调用能力","文本生成能力"],"capabilities":["工具调用","文本生成","深度思考"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}},{"id":"glm-5-3-flash-260828","name":"glm-5-3-flash-260828","display_name":"glm-5-3-flash-260828","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"last_updated":"2026-10-18T12:21:35Z","vision":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1024000,"output":128000,"requests_per_minute":500},"metadata":{"source":"volcengine-docs","max_thinking_tokens":128000,"max_input_tokens":1024000,"canonical_id":"glm-5-3-flash","detail_url":"https://ark.volcengine.com/region:cn-beijing/model/detail?name=glm-5-3-flash","section_titles":["上下文缓存能力","工具调用能力","文本生成能力","视觉理解能力"],"capabilities":["多模态理解","工具调用","文本生成","深度思考"],"raw_limits":["上下文窗口: 1024k 最大输入: 1024k 最大回答(默认 4k): 128k 最大思维链: 128k","最大 RPM: 500 最大 TPM: 1000000"],"features":["context-cache"]}}]},"ppinfra":{"id":"ppinfra","name":"PPInfra","display_name":"PPInfra","updated_at":"2026-10-18T20:13:12.471Z","models":[{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","display_name":"Qwen3.8 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5.3-flash","name":"GLM 5.3 Flash","display_name":"GLM 5.3 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy4-preview","name":"Hy4 Preview","display_name":"Hy4 Preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-0731-p","name":"deepseek/deepseek-v4-flash-0731-p","display_name":"deepseek/deepseek-v4-flash-0731-p","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"deepseek/deepseek-v4-pro-0813-p","name":"deepseek v4 pro 0813 p","display_name":"deepseek v4 pro 0813 p","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"deepseek/deepseek-v4.1-flash-z","name":"DeepseekFlash","display_name":"DeepseekFlash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"zai-org/glm-5.3-p","name":"zai-org/glm-5.3-p","display_name":"zai-org/glm-5.3-p","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","display_name":"DeepSeek V4.1 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"zai-org/glm-5.3","name":"GLM 5.3","display_name":"GLM 5.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","display_name":"DeepSeek V4 Flash 0731","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","display_name":"Kimi K3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":1048576},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5.2","name":"GLM 5.2","display_name":"GLM 5.2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","display_name":"Kimi K2.7 Code","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m3","name":"MiniMax-M3","display_name":"MiniMax-M3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","display_name":"DeepSeek V4 Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"inclusionai/ling-3.1-flash","name":"Ling 3.1 Flash","display_name":"Ling 3.1 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"stepfun/step-5-preview","name":"Step 5 Preview","display_name":"Step 5 Preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"xiaomimimo/mimo-v2.6-flash","name":"MiMo V2.6 Flash","display_name":"MiMo V2.6 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"xiaomimimo/mimo-v2.6-pro","name":"MiMo V2.6 Pro","display_name":"MiMo V2.6 Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","display_name":"Qwen3.7 Plus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":991000,"output":131000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","display_name":"Qwen3.8 27B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","display_name":"Qwen3.8 2.4T A95B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","display_name":"Qwen3.8 Max","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xiaomimimo/mimo-v2.5","name":"Xiaomi MiMo V2.5","display_name":"Xiaomi MiMo V2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","display_name":"Qwen3.7 Max","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xiaomimimo/mimo-v2.5-pro","name":"Xiaomi MiMo V2.5 Pro","display_name":"Xiaomi MiMo V2.5 Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","display_name":"Qwen3.6 27B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","display_name":"Kimi K2.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5.1","name":"GLM 5.1","display_name":"GLM 5.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7-highspeed","display_name":"MiniMax M2.7-highspeed","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","display_name":"MiniMax M2.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","display_name":"Qwen3.5 27B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","display_name":"Qwen3.5 122B A10B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","display_name":"Qwen3.5 35B A3B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","display_name":"Qwen3.5 397B A17B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","display_name":"MiniMax M2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.1-h","name":"minimax/minimax-m2.1","display_name":"minimax/minimax-m2.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"zai-org/glm-5","name":"GLM 5","display_name":"GLM 5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":202800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-ocr-2","name":"DeepSeek OCR 2","display_name":"DeepSeek OCR 2","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","display_name":"Kimi K2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-4.7-flash","name":"GLM 4.7 Flash","display_name":"GLM 4.7 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":200000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-4.7","name":"GLM 4.7","display_name":"GLM 4.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/autoglm-phone-9b-multilingual","name":"AutoGLM Phone 9B Multilingual","display_name":"AutoGLM Phone 9B Multilingual","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":65536,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","display_name":"Kimi K2 Thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":100352},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","display_name":"Qwen3.6 35B A3B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-4.6v","name":"GLM 4.6v","display_name":"GLM 4.6v","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"zai-org/glm-4.6","name":"GLM 4.6","display_name":"GLM 4.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 Instruct 0905","display_name":"Kimi K2 Instruct 0905","type":"chat","reasoning":{"supported":false},"tool_call":true,"limit":{"context":262144,"output":100352},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","display_name":"Kimi K2 Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"limit":{"context":131072,"output":100352},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"zai-org/glm-4.5v","name":"GLM 4.5V","display_name":"GLM 4.5V","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":65536,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"minimaxai/minimax-m1-80k","name":"MiniMaxAI/MiniMax-M1-80k","display_name":"MiniMaxAI/MiniMax-M1-80k","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":128000,"output":40000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3.5-omni-flash","name":"Qwen3.5 Omni Flash","display_name":"Qwen3.5 Omni Flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"thudm/glm-4.1v-9b-thinking","name":"GLM 4.1V 9B Thinking","display_name":"GLM 4.1V 9B Thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"limit":{"context":65536,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"pprouter/auto","name":"PPRouter Auto","display_name":"PPRouter Auto","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"pprouter/fusion","name":"pprouter/fusion","display_name":"pprouter/fusion","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"pprouter/mom","name":"pprouter/mom","display_name":"pprouter/mom","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"elephant","name":"Ling 2.6 Flash","display_name":"Ling 2.6 Flash","type":"chat","reasoning":{"supported":false},"tool_call":true,"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"ai_infer_test_2","name":"ai_infer_test_2","display_name":"ai_infer_test_2","type":"chat","reasoning":{"supported":false},"tool_call":true,"limit":{"context":200000,"output":200000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"ai_infer_test_3","name":"ai_infer_test_3","display_name":"ai_infer_test_3","type":"chat","reasoning":{"supported":false},"tool_call":true,"limit":{"context":200000,"output":200000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"ppio-4b","name":"PPIO 4B","display_name":"PPIO 4B","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"baidu/ernie-5.0-thinking-exp","name":"Ernie 5.0 Thinking Exp","display_name":"Ernie 5.0 Thinking Exp","type":"chat","reasoning":{"supported":true},"tool_call":false,"limit":{"context":183000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"baidu/ernie-5.0-thinking-preview","name":"Ernie 5.0 Thinking Preview","display_name":"Ernie 5.0 Thinking Preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":183000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kwaipilot/kat-dev-72b-exp","name":"KAT-Dev-72B-Exp","display_name":"KAT-Dev-72B-Exp","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":131072,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"zai-org/glm-4.5-air","name":"GLM 4.5 Air","display_name":"GLM 4.5 Air","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"limit":{"context":131072,"output":98304},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-omni-30b-a3b-captioner","name":"qwen/qwen3-omni-30b-a3b-captioner","display_name":"qwen/qwen3-omni-30b-a3b-captioner","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192},"metadata":{"source":"public-provider-conf"},"vision":false}],"metadata":{"source":"public-provider-conf"}},"custom-provider":{"id":"custom-provider","name":"custom provider","display_name":"custom provider","description":"Generated first-tier fallback catalog combining official high-signal chat, coding, reasoning, and frontier model metadata.","updated_at":"2026-09-30T00:00:00.000Z","doc":"docs/custom-provider.md","tags":["fallback","official","generated","chat","coding","reasoning"],"models":[{"id":"claude-fable-5","name":"Claude Fable 5","family":"claude-fable","display_name":"Claude Fable 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"knowledge":"2026-01","release_date":"2026-06-09","last_updated":"2026-06-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"limit":{"context":1000000,"output":128000},"metadata":{"selection":["creative","agentic","reasoning"],"lifecycle":"legacy","apiStatus":"active-legacy","notes":["Anthropic lists this model as Active (legacy); retirement is scheduled no sooner than June 9, 2027."],"sourceProvider":"anthropic","sourceProviderName":"Anthropic","sourceApiUrl":"https://api.anthropic.com/v1/models","sourceDocs":["https://platform.claude.com/docs/en/about-claude/models/overview","https://docs.anthropic.com/en/api/models-list","https://www.anthropic.com/claude-opus-5-5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-fable-5-1","name":"Claude Fable 5.1","family":"claude-fable","display_name":"Claude Fable 5.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"limit":{"context":1000000,"output":128000},"metadata":{"selection":["frontier","agentic","reasoning","long-context"],"lifecycle":"active","apiStatus":"active","notes":["Retirement is scheduled no sooner than September 1, 2027."],"sourceProvider":"anthropic","sourceProviderName":"Anthropic","sourceApiUrl":"https://api.anthropic.com/v1/models","sourceDocs":["https://platform.claude.com/docs/en/about-claude/models/overview","https://docs.anthropic.com/en/api/models-list","https://www.anthropic.com/claude-opus-5-5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on; thinking.type = \"enabled\" or \"disabled\" is rejected.","Forced tool use is not supported: tool_choice any or a named tool returns a 400 invalid_request_error.","One-hour cache writes are billed at $20 per million tokens."]}}},{"id":"claude-haiku-4-5","name":"Claude Haiku 4.5","family":"claude-haiku","display_name":"Claude Haiku 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"structured_output":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"limit":{"context":200000,"output":64000},"metadata":{"selection":["fast","near-frontier","cost-efficient"],"lifecycle":"active","snapshotId":"claude-haiku-4-5-20251001","sourceProvider":"anthropic","sourceProviderName":"Anthropic","sourceApiUrl":"https://api.anthropic.com/v1/models","sourceDocs":["https://platform.claude.com/docs/en/about-claude/models/overview","https://docs.anthropic.com/en/api/models-list","https://www.anthropic.com/claude-opus-5-5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-opus-5","name":"Claude Opus 5","family":"claude-opus","display_name":"Claude Opus 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":1000000,"output":128000},"metadata":{"selection":["sota","agentic-coding","reasoning"],"lifecycle":"active","sourceProvider":"anthropic","sourceProviderName":"Anthropic","sourceApiUrl":"https://api.anthropic.com/v1/models","sourceDocs":["https://platform.claude.com/docs/en/about-claude/models/overview","https://docs.anthropic.com/en/api/models-list","https://www.anthropic.com/claude-opus-5-5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","high","xhigh","max"],"notes":["Thinking can be disabled with thinking.type = \"disabled\" only at effort high or lower; combining disabled with xhigh or max returns a 400 error."],"default_enabled":true,"mode":"effort","effort":"high","visibility":"hidden"}}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5","family":"claude-opus","display_name":"Claude Opus 5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"limit":{"context":1000000,"output":128000},"metadata":{"selection":["latest","agentic-coding","reasoning","cost-efficient"],"lifecycle":"active","apiStatus":"active","pricingBasis":"standard","availability":["api"],"notes":["Adaptive thinking is always on and cannot be disabled.","Preserve prior thinking blocks for API accounts created on or after August 31, 2026."],"sourceProvider":"anthropic","sourceProviderName":"Anthropic","sourceApiUrl":"https://api.anthropic.com/v1/models","sourceDocs":["https://platform.claude.com/docs/en/about-claude/models/overview","https://docs.anthropic.com/en/api/models-list","https://www.anthropic.com/claude-opus-5-5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"adaptive","interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"]}}},{"id":"claude-sonnet-5","name":"Claude Sonnet 5","family":"claude-sonnet","display_name":"Claude Sonnet 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1000000,"output":128000},"metadata":{"selection":["balanced","coding","reasoning"],"lifecycle":"active","notes":["The $2/$10 introductory pricing became the standard price on September 1, 2026."],"sourceProvider":"anthropic","sourceProviderName":"Anthropic","sourceApiUrl":"https://api.anthropic.com/v1/models","sourceDocs":["https://platform.claude.com/docs/en/about-claude/models/overview","https://docs.anthropic.com/en/api/models-list","https://www.anthropic.com/claude-opus-5-5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","family":"deepseek-flash","display_name":"DeepSeek V4 Flash","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.44,"output":1.32,"reasoning":1.32,"cache_read":0.014},"limit":{"context":1000000,"output":384000},"metadata":{"selection":["latest","cost-efficient","long-context"],"lifecycle":"active","pricingBasis":"peak","notes":["USD per million tokens at peak hours; official off-peak prices are half these rates.","Temperature is effective only with thinking disabled; thinking mode ignores sampling parameters."],"sourceProvider":"deepseek","sourceProviderName":"DeepSeek","sourceApiUrl":"https://api.deepseek.com/models","sourceDocs":["https://api-docs.deepseek.com/quick_start/pricing/","https://api-docs.deepseek.com/api/create-chat-completion","https://api-docs.deepseek.com/guides/thinking_mode/","https://api-docs.deepseek.com/updates/"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","family":"deepseek-flash","display_name":"DeepSeek V4 Flash Vision Exp","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"knowledge":"2025-05","release_date":"2026-08-21","last_updated":"2026-08-21","open_weights":true,"experimental":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.44,"output":1.32,"reasoning":1.32,"cache_read":0.014},"limit":{"context":1000000,"output":384000},"metadata":{"selection":["latest","multimodal","cost-efficient","long-context"],"lifecycle":"preview","pricingBasis":"peak","notes":["USD per million tokens at peak hours; official off-peak prices are half these rates.","Temperature is effective only with thinking disabled; thinking mode ignores sampling parameters."],"sourceProvider":"deepseek","sourceProviderName":"DeepSeek","sourceApiUrl":"https://api.deepseek.com/models","sourceDocs":["https://api-docs.deepseek.com/quick_start/pricing/","https://api-docs.deepseek.com/api/create-chat-completion","https://api-docs.deepseek.com/guides/thinking_mode/","https://api-docs.deepseek.com/updates/"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","family":"deepseek-thinking","display_name":"DeepSeek V4 Pro","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-08-13","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":1.32,"output":3.96,"reasoning":3.96,"cache_read":0.044},"limit":{"context":1000000,"output":384000},"metadata":{"selection":["latest","frontier","long-context"],"lifecycle":"active","pricingBasis":"peak","notes":["USD per million tokens at peak hours; official off-peak prices are half these rates.","Temperature is effective only with thinking disabled; thinking mode ignores sampling parameters."],"sourceProvider":"deepseek","sourceProviderName":"DeepSeek","sourceApiUrl":"https://api.deepseek.com/models","sourceDocs":["https://api-docs.deepseek.com/quick_start/pricing/","https://api-docs.deepseek.com/api/create-chat-completion","https://api-docs.deepseek.com/guides/thinking_mode/","https://api-docs.deepseek.com/updates/"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-flash","name":"DeepSeek V4.1 Flash","family":"deepseek-flash","display_name":"DeepSeek V4.1 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"release_date":"2026-09-10","last_updated":"2026-09-10","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.3,"output":1.2,"reasoning":1.2,"cache_read":0.006},"limit":{"context":1000000,"output":384000},"metadata":{"selection":["latest","frontier","reasoning","multimodal","long-context"],"lifecycle":"active","pricingBasis":"peak","notes":["USD per million tokens at peak hours; official off-peak prices are half these rates.","Temperature is effective only with thinking disabled; thinking mode ignores sampling parameters.","Successor to the retired V4 Flash and V4 Flash Vision Exp models. The legacy model names deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route to this model and bill at Flash rates."],"sourceProvider":"deepseek","sourceProviderName":"DeepSeek","sourceApiUrl":"https://api.deepseek.com/models","sourceDocs":["https://api-docs.deepseek.com/quick_start/pricing/","https://api-docs.deepseek.com/api/create-chat-completion","https://api-docs.deepseek.com/guides/thinking_mode/","https://api-docs.deepseek.com/updates/"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","family":"gemini-pro","display_name":"Gemini 3.1 Pro Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":2,"output":12,"cache_read":0.2},"limit":{"context":1048576,"output":65536},"metadata":{"selection":["frontier","multimodal","coding"],"lifecycle":"preview","pricingBasis":"input-up-to-200k","notes":["Inputs above 200K tokens are billed at $4 input / $18 output with $0.40 cached input."],"sourceProvider":"gemini","sourceProviderName":"Gemini","sourceApiUrl":"https://generativelanguage.googleapis.com/v1beta/models","sourceDocs":["https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/gemini-3","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","https://ai.google.dev/gemini-api/docs/latest-model","https://ai.google.dev/gemini-api/docs/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","family":"gemini-flash","display_name":"Gemini 3.5 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"limit":{"context":1048576,"output":65536},"metadata":{"selection":["fast","multimodal","reasoning"],"lifecycle":"active","sourceProvider":"gemini","sourceProviderName":"Gemini","sourceApiUrl":"https://generativelanguage.googleapis.com/v1beta/models","sourceDocs":["https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/gemini-3","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","https://ai.google.dev/gemini-api/docs/latest-model","https://ai.google.dev/gemini-api/docs/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","family":"gemini-flash-lite","display_name":"Gemini 3.5 Flash Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"limit":{"context":1048576,"output":65536},"metadata":{"selection":["fast","cost-efficient","multimodal"],"lifecycle":"active","sourceProvider":"gemini","sourceProviderName":"Gemini","sourceApiUrl":"https://generativelanguage.googleapis.com/v1beta/models","sourceDocs":["https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/gemini-3","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","https://ai.google.dev/gemini-api/docs/latest-model","https://ai.google.dev/gemini-api/docs/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","family":"gemini-flash","display_name":"Gemini 3.6 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":65536},"metadata":{"selection":["fast","multimodal","reasoning"],"lifecycle":"active","pricingBasis":"standard-introductory","pricingValidUntil":"2026-12-31","notes":["Pricing shown is the introductory Global rate through December 31, 2026; standard pricing from January 1, 2027 is $1.50 input / $7.50 output with $0.15 cached input."],"sourceProvider":"gemini","sourceProviderName":"Gemini","sourceApiUrl":"https://generativelanguage.googleapis.com/v1beta/models","sourceDocs":["https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/gemini-3","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","https://ai.google.dev/gemini-api/docs/latest-model","https://ai.google.dev/gemini-api/docs/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"medium","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"notes":["The default thinkingLevel is medium."]}}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","family":"gemini-flash","display_name":"Gemini 3.7 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-31","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":65536},"metadata":{"selection":["latest","fast","multimodal","reasoning"],"lifecycle":"active","pricingBasis":"standard-introductory","pricingValidUntil":"2026-12-31","notes":["Knowledge cutoff is March 2026; some domains remain limited to January 2025."],"sourceProvider":"gemini","sourceProviderName":"Gemini","sourceApiUrl":"https://generativelanguage.googleapis.com/v1beta/models","sourceDocs":["https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/gemini-3","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","https://ai.google.dev/gemini-api/docs/latest-model","https://ai.google.dev/gemini-api/docs/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"medium","level_options":["low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"notes":["The thinkingLevel parameter does not accept minimal."]}}},{"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","family":"gemini-flash","display_name":"Gemini 3.8 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"knowledge":"2026-03","release_date":"2026-09-02","last_updated":"2026-09-02","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":65536},"metadata":{"selection":["latest","fast","multimodal","reasoning"],"lifecycle":"active","pricingBasis":"standard-introductory","pricingValidUntil":"2026-12-31","notes":["Pricing shown is the introductory Global rate through December 31, 2026; standard pricing from January 1, 2027 is $1.50 input / $7.50 output with $0.15 cached input.","Knowledge cutoff is March 2026; some domains remain limited to January 2025."],"sourceProvider":"gemini","sourceProviderName":"Gemini","sourceApiUrl":"https://generativelanguage.googleapis.com/v1beta/models","sourceDocs":["https://ai.google.dev/gemini-api/docs/models","https://ai.google.dev/gemini-api/docs/gemini-3","https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash","https://ai.google.dev/gemini-api/docs/latest-model","https://ai.google.dev/gemini-api/docs/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"medium","level_options":["low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"notes":["The thinkingLevel parameter does not accept minimal.","The default thinkingLevel is medium."]}}},{"id":"glm-5.2","name":"GLM-5.2","family":"glm","display_name":"GLM-5.2","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"release_date":"2026-06-16","last_updated":"2026-06-16","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["coding","long-context","optional-thinking"],"lifecycle":"active","sourceProvider":"zhipu","sourceProviderName":"Zhipu","sourceDocs":["https://docs.z.ai/guides/llm/glm-5.3","https://docs.z.ai/guides/vlm/glm-5.3-flash","https://docs.z.ai/guides/llm/glm-5.2","https://docs.z.ai/guides/capabilities/thinking-mode","https://docs.z.ai/guides/overview/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","minimal","low","medium","high","xhigh","max"],"continuation":["thinking_blocks"],"notes":["none and minimal stop thinking; low and medium map to high; xhigh maps to max.","The same page also states that low is only supported by GLM-5.3 and GLM-5.3-Flash, which conflicts with the GLM-5.2 option list."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"glm-5.3","name":"GLM-5.3","family":"glm","display_name":"GLM-5.3","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"release_date":"2026-08-18","last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["latest","coding","long-context","reasoning"],"lifecycle":"active","notes":["Zhipu release notes list the release date as 2026-08-18; the official model blog references 2026-08-14."],"sourceProvider":"zhipu","sourceProviderName":"Zhipu","sourceDocs":["https://docs.z.ai/guides/llm/glm-5.3","https://docs.z.ai/guides/vlm/glm-5.3-flash","https://docs.z.ai/guides/llm/glm-5.2","https://docs.z.ai/guides/capabilities/thinking-mode","https://docs.z.ai/guides/overview/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","high","max"],"continuation":["thinking_blocks"],"notes":["Thinking cannot be disabled; reasoning_effort defaults to max. Set thinking.clear_thinking to false to preserve reasoning across turns."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"glm-5.3-flash","name":"GLM-5.3 Flash","family":"glm","display_name":"GLM-5.3 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"release_date":"2026-08-26","last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text","image","video","file"],"output":["text"]},"cost":{"input":0.15,"output":0.5,"cache_read":0.03,"cache_write":0},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["latest","multimodal","coding","cost-efficient"],"lifecycle":"active","notes":["The $0.075/$0.25/$0.015 promotional pricing ended on September 10, 2026; the current standard rate is $0.15 input / $0.50 output with $0.03 cached input."],"sourceProvider":"zhipu","sourceProviderName":"Zhipu","sourceDocs":["https://docs.z.ai/guides/llm/glm-5.3","https://docs.z.ai/guides/vlm/glm-5.3-flash","https://docs.z.ai/guides/llm/glm-5.2","https://docs.z.ai/guides/capabilities/thinking-mode","https://docs.z.ai/guides/overview/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","high","max"],"continuation":["thinking_blocks"],"notes":["Thinking cannot be disabled; reasoning_effort defaults to max. Set thinking.clear_thinking to false to preserve reasoning across turns."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"glm-5.3-flashx","name":"GLM-5.3 FlashX","family":"glm","display_name":"GLM-5.3 FlashX","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"last_updated":"2026-09-20","modalities":{"input":["text","image","video","file"],"output":["text"]},"cost":{"input":0.37,"output":1.25,"cache_read":0.075,"cache_write":0},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["latest","multimodal","fast","cost-efficient"],"lifecycle":"active","notes":["FlashX serves GLM-5.3-Flash at about 200 tokens per second and is not yet available on the GLM Coding Plan."],"sourceProvider":"zhipu","sourceProviderName":"Zhipu","sourceDocs":["https://docs.z.ai/guides/llm/glm-5.3","https://docs.z.ai/guides/vlm/glm-5.3-flash","https://docs.z.ai/guides/llm/glm-5.2","https://docs.z.ai/guides/capabilities/thinking-mode","https://docs.z.ai/guides/overview/pricing"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["low","high","max"],"notes":["Thinking cannot be disabled; reasoning_effort defaults to max. Set thinking.clear_thinking to false to preserve reasoning across turns."],"default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"gpt-5.5","name":"GPT-5.5","family":"gpt","display_name":"GPT-5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["frontier","coding","reasoning"],"lifecycle":"active","apiStatus":"active","availability":["api","chatgpt","codex"],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6","name":"GPT-5.6","family":"gpt","display_name":"GPT-5.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["frontier","coding","reasoning"],"lifecycle":"active","apiStatus":"active","availability":["api","chatgpt","codex"],"pricingValidUntil":"2026-11-21","notes":["The gpt-5.6 alias routes requests to gpt-5.6-sol; the two names share pricing.","Promotional pricing is available at least through November 21, 2026.","Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request."],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","family":"gpt-luna","display_name":"GPT-5.6 Luna","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["fast","high-volume","reasoning","cost-efficient"],"lifecycle":"active","apiStatus":"active","availability":["api","chatgpt","codex"],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","family":"gpt","display_name":"GPT-5.6 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["frontier","coding","reasoning"],"lifecycle":"active","apiStatus":"active","availability":["api","chatgpt","codex"],"pricingValidUntil":"2026-11-21","notes":["Promotional pricing is available at least through November 21, 2026.","Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request."],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","family":"gpt-terra","display_name":"GPT-5.6 Terra","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["balanced","coding","reasoning","cost-efficient"],"lifecycle":"active","apiStatus":"active","availability":["api","chatgpt","codex"],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-6-astra","name":"GPT-6 Astra","family":"gpt","display_name":"GPT-6 Astra","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"knowledge":"2026-04-30","release_date":"2026-09-03","last_updated":"2026-09-03","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["frontier","sota","coding","reasoning"],"lifecycle":"active","apiStatus":"active","availability":["api"],"notes":["Does not support the none reasoning effort level.","Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request.","Tool calling requires the Responses API."],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","high","xhigh","max"],"verbosity_options":["low","medium","high"],"default_enabled":true,"mode":"effort","verbosity":"medium","visibility":"hidden"}}},{"id":"gpt-6-luna","name":"GPT-6 Luna","family":"gpt","display_name":"GPT-6 Luna","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["latest","fast","high-volume","cost-efficient","reasoning"],"lifecycle":"active","apiStatus":"active","availability":["api"],"pricingBasis":"standard-up-to-272k-input","notes":["For prompts above 272K input tokens, input and cache rates double and output is 1.5x for the full request."],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"visibility":"hidden","notes":["The default reasoning effort is medium.","Chat Completions function calling requires reasoning_effort = none; use Responses for tool calling with reasoning enabled."]}}},{"id":"gpt-6-sol","name":"GPT-6 Sol","family":"gpt","display_name":"GPT-6 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["latest","coding","agentic","reasoning"],"lifecycle":"active","apiStatus":"active","availability":["api"],"pricingBasis":"standard-up-to-272k-input","notes":["For prompts above 272K input tokens, input and cache rates double and output is 1.5x for the full request."],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"visibility":"hidden","notes":["The default reasoning effort is medium.","Chat Completions function calling requires reasoning_effort = none; use Responses for tool calling with reasoning enabled."]}}},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","family":"gpt","display_name":"GPT-6.1 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"limit":{"context":1050000,"output":128000},"metadata":{"selection":["latest","coding","agentic","reasoning"],"lifecycle":"active","apiStatus":"active","availability":["api"],"pricingBasis":"standard-up-to-272k-input","notes":["Does not support the none reasoning effort level.","Prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request."],"sourceProvider":"openai","sourceProviderName":"OpenAI","sourceApiUrl":"https://api.openai.com/v1/models","sourceDocs":["https://developers.openai.com/api/docs/models","https://developers.openai.com/api/docs/guides/latest-model","https://developers.openai.com/api/docs/models/gpt-6.1-sol","https://developers.openai.com/api/docs/models/gpt-6-sol","https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/models/gpt-5.6-sol","https://developers.openai.com/api/docs/models/gpt-5.6-terra","https://developers.openai.com/api/docs/models/gpt-5.6-luna","https://developers.openai.com/api/docs/models/gpt-5.5"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh","max"],"visibility":"hidden","notes":["The default reasoning effort is medium."]}}},{"id":"kimi-k2.5","name":"Kimi K2.5","family":"kimi-k2.5","display_name":"Kimi K2.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"}],"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.6,"output":3,"cache_read":0.1},"limit":{"context":262144,"output":262144},"metadata":{"selection":["compatibility","multimodal","reasoning","coding"],"lifecycle":"legacy","apiStatus":"retired","officialSunsetDate":"2026-08-31","notes":["Retained for third-party metadata fallback. Kimi retired the kimi-k2.5 and moonshot-v1 series on August 31, 2026; calls to these model names now return a 404 error, and inclusion does not imply official availability. Pricing is historical."],"sourceProvider":"kimi","sourceProviderName":"Kimi","sourceApiUrl":"https://api.moonshot.ai/v1/models","sourceDocs":["https://platform.kimi.ai/docs/models","https://platform.kimi.ai/docs/api/models-overview","https://platform.kimi.ai/docs/api/chat","https://platform.kimi.ai/docs/guide/kimi-k3-quickstart","https://platform.kimi.ai/docs/guide/kimi-k2-7-code-quickstart","https://platform.kimi.ai/docs/pricing/chat-k3","https://platform.kimi.ai/docs/pricing/chat-k27-code"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Temperature is fixed at 1.0 with thinking enabled and 0.6 with thinking disabled."],"default_enabled":true}}},{"id":"kimi-k2.6","name":"Kimi K2.6","family":"kimi-k2.6","display_name":"Kimi K2.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"}],"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.95,"output":4,"cache_read":0.16},"limit":{"context":262144,"output":262144},"metadata":{"selection":["multimodal","coding","optional-thinking"],"lifecycle":"active","sourceProvider":"kimi","sourceProviderName":"Kimi","sourceApiUrl":"https://api.moonshot.ai/v1/models","sourceDocs":["https://platform.kimi.ai/docs/models","https://platform.kimi.ai/docs/api/models-overview","https://platform.kimi.ai/docs/api/chat","https://platform.kimi.ai/docs/guide/kimi-k3-quickstart","https://platform.kimi.ai/docs/guide/kimi-k2-7-code-quickstart","https://platform.kimi.ai/docs/pricing/chat-k3","https://platform.kimi.ai/docs/pricing/chat-k27-code"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"notes":["Temperature is fixed at 1.0 with thinking enabled and 0.6 with thinking disabled."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","family":"kimi-k2.7-code","display_name":"Kimi K2.7 Code","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"release_date":"2026-06-12","last_updated":"2026-08-31","modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.95,"output":4,"cache_read":0.19},"limit":{"context":262144,"output":262144},"metadata":{"selection":["latest","coding","agentic"],"lifecycle":"active","sourceProvider":"kimi","sourceProviderName":"Kimi","sourceApiUrl":"https://api.moonshot.ai/v1/models","sourceDocs":["https://platform.kimi.ai/docs/models","https://platform.kimi.ai/docs/api/models-overview","https://platform.kimi.ai/docs/api/chat","https://platform.kimi.ai/docs/guide/kimi-k3-quickstart","https://platform.kimi.ai/docs/guide/kimi-k2-7-code-quickstart","https://platform.kimi.ai/docs/pricing/chat-k3","https://platform.kimi.ai/docs/pricing/chat-k27-code"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"notes":["Thinking is always enabled and preserved. Disabling thinking is unsupported; temperature is fixed at 1.0."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}}},{"id":"kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","family":"kimi-k2.7-code-highspeed","display_name":"Kimi K2.7 Code Highspeed","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":1.9,"output":8,"cache_read":0.38},"limit":{"context":262144,"output":262144},"metadata":{"selection":["latest","coding","agentic"],"lifecycle":"active","notes":["The official API release date for this endpoint is not documented; it serves the same model as kimi-k2.7-code with faster output."],"sourceProvider":"kimi","sourceProviderName":"Kimi","sourceApiUrl":"https://api.moonshot.ai/v1/models","sourceDocs":["https://platform.kimi.ai/docs/models","https://platform.kimi.ai/docs/api/models-overview","https://platform.kimi.ai/docs/api/chat","https://platform.kimi.ai/docs/guide/kimi-k3-quickstart","https://platform.kimi.ai/docs/guide/kimi-k2-7-code-quickstart","https://platform.kimi.ai/docs/pricing/chat-k3","https://platform.kimi.ai/docs/pricing/chat-k27-code"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"notes":["Thinking is always enabled and preserved. Disabling thinking is unsupported; temperature is fixed at 1.0."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"fixed"}}},{"id":"kimi-k3","name":"Kimi K3","family":"kimi-k3","display_name":"Kimi K3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"release_date":"2026-07-16","last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":3,"output":15,"cache_read":0.3},"limit":{"context":1048576,"output":1048576},"metadata":{"selection":["latest","multimodal","long-context","agentic"],"lifecycle":"active","sourceProvider":"kimi","sourceProviderName":"Kimi","sourceApiUrl":"https://api.moonshot.ai/v1/models","sourceDocs":["https://platform.kimi.ai/docs/models","https://platform.kimi.ai/docs/api/models-overview","https://platform.kimi.ai/docs/api/chat","https://platform.kimi.ai/docs/guide/kimi-k3-quickstart","https://platform.kimi.ai/docs/guide/kimi-k2-7-code-quickstart","https://platform.kimi.ai/docs/pricing/chat-k3","https://platform.kimi.ai/docs/pricing/chat-k27-code"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","high","max"],"continuation":["thinking_blocks"],"notes":["Thinking is always enabled; reasoning_effort defaults to max.","max_completion_tokens defaults to 131072 and can reach 1048576 within the shared input/output context window."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","family":"minimax","display_name":"MiniMax-M2.7","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":false,"release_date":"2026-03-18","last_updated":"2026-03-18","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"limit":{"context":204800,"output":131072},"metadata":{"selection":["latest","coding","agentic"],"lifecycle":"active","sourceProvider":"minimax","sourceProviderName":"MiniMax","sourceDocs":["https://platform.minimax.io/docs/guides/models-intro","https://platform.minimax.io/docs/api-reference/api-overview","https://platform.minimax.io/docs/guides/text-ai-coding-tools"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"default_enabled":true}}},{"id":"MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","family":"minimax","display_name":"MiniMax-M2.7-highspeed","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":false,"release_date":"2026-03-18","last_updated":"2026-03-18","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"limit":{"context":204800,"output":131072},"metadata":{"selection":["latest","fast","coding"],"lifecycle":"active","sourceProvider":"minimax","sourceProviderName":"MiniMax","sourceDocs":["https://platform.minimax.io/docs/guides/models-intro","https://platform.minimax.io/docs/api-reference/api-overview","https://platform.minimax.io/docs/guides/text-ai-coding-tools"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"default_enabled":true}}},{"id":"MiniMax-M3","name":"MiniMax-M3","family":"minimax","display_name":"MiniMax-M3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"release_date":"2026-06-01","last_updated":"2026-06-25","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"limit":{"context":1000000,"output":128000},"metadata":{"selection":["latest","multimodal","long-context","agentic"],"lifecycle":"active","notes":["Pay-as-you-go prices are the permanent 50%-off rates in USD per million tokens for the standard tier at up to 512k input tokens; above 512k input the standard tier is $0.60 input / $2.40 output with $0.12 cache read. The priority tier is 1.5x the standard tier."],"sourceProvider":"minimax","sourceProviderName":"MiniMax","sourceDocs":["https://platform.minimax.io/docs/guides/models-intro","https://platform.minimax.io/docs/api-reference/api-overview","https://platform.minimax.io/docs/guides/text-ai-coding-tools"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"notes":["Thinking is controlled with thinking.type = \"adaptive\" or \"disabled\"; M2.x models accept disabled but keep thinking on.","The OpenAI-compatible API page states thinking is on by default when omitted, while the Anthropic-compatible page states it is off by default."],"default_enabled":true,"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"qwen3-coder-flash","name":"Qwen3 Coder Flash","family":"qwen-coder","display_name":"Qwen3 Coder Flash","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"structured_output":false,"last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.3,"output":1.5,"cache_read":0.03,"cache_write":0.375},"limit":{"context":1000000,"output":65536},"metadata":{"selection":["coding","agentic"],"lifecycle":"legacy","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"input-up-to-32k","notes":["Alibaba lists this model as legacy and no longer recommended. Function calling is unsupported on the International and Global endpoints; the China (Beijing) endpoint documents it as supported.","Cache prices, when present, refer to explicit caching. Longer inputs may use higher pricing tiers."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":false,"default_enabled":false}}},{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","family":"qwen-coder","display_name":"Qwen3 Coder Next","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"structured_output":false,"last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.3,"output":1.5},"limit":{"context":262144,"output":65536},"metadata":{"selection":["coding","agentic"],"lifecycle":"legacy","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"input-up-to-32k","notes":["Alibaba lists this model as legacy and no longer recommended. The model detail page lists function calling as unsupported even though its prose claims multi-turn tool support.","Cache prices, when present, refer to explicit caching. Longer inputs may use higher pricing tiers."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":false,"default_enabled":false}}},{"id":"qwen3-coder-plus","name":"Qwen3 Coder Plus","family":"qwen-coder","display_name":"Qwen3 Coder Plus","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"structured_output":false,"last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"limit":{"context":1000000,"output":65536},"metadata":{"selection":["coding","agentic"],"lifecycle":"legacy","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"input-up-to-32k","notes":["Alibaba lists this model as legacy and no longer recommended. Function calling is unsupported on the International and Global endpoints; the China (Beijing) endpoint documents it as supported.","Cache prices, when present, refer to explicit caching. Longer inputs may use higher pricing tiers."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":false,"default_enabled":false}}},{"id":"qwen3.7-flash","name":"Qwen3.7 Flash","family":"qwen","display_name":"Qwen3.7 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"budget"}],"last_updated":"2026-09-14","modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.03,"output":0.13,"cache_read":0.003,"cache_write":0.038},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["fast","multimodal","reasoning","cost-efficient"],"lifecycle":"active","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"input-up-to-32k","notes":["Prices shown are the up-to-32k-input tier; 32k-256k input is billed at $0.10 input / $0.40 output with $0.125 explicit cache creation and $0.010 cache read, and 256k-1m input at $0.20 / $0.80 with $0.25 creation and $0.020 read.","Cache prices refer to explicit caching."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"budget":{"max":262144,"default":262144,"unit":"tokens"},"continuation":["thinking_blocks"],"notes":["Thinking mode has a 983616-token input limit and a separate 262144-token reasoning budget.","Set preserve_thinking=true to retain reasoning_content across turns.","The official reasoning.effort model list does not name the Qwen3.7 series."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"budget"}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus","family":"qwen","display_name":"Qwen3.7 Plus","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"budget"}],"last_updated":"2026-08-31","modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["multimodal","reasoning","coding"],"lifecycle":"active","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"input-up-to-256k","notes":["Thinking mode has a 983616-token input limit and a separate 262144-token reasoning budget.","Cache prices refer to explicit caching. Longer inputs may use higher pricing tiers.","The official reasoning.effort model list does not name the Qwen3.7 series, so no effort range is recorded for this model."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"budget":{"max":262144,"default":262144,"unit":"tokens"},"continuation":["thinking_blocks"],"notes":["enable_thinking toggles reasoning; thinking_budget caps it. Set preserve_thinking=true to retain reasoning_content across turns."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"budget"}}},{"id":"qwen3.8-flash","name":"Qwen3.8 Flash","family":"qwen","display_name":"Qwen3.8 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"budget"},{"type":"effort","values":["none","low","medium","xhigh"],"exclusive_with":["budget"]}],"last_updated":"2026-08-31","modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.15,"output":0.47,"cache_read":0.016,"cache_write":0.2},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["multimodal","reasoning","coding"],"lifecycle":"active","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"standard","notes":["Thinking mode has a 983616-token input limit and a separate 262144-token reasoning budget.","Cache prices refer to explicit caching. Longer inputs may use higher pricing tiers.","reasoning_effort defaults to xhigh and accepts xhigh, medium, and low; max maps to xhigh, minimal maps to low, and none disables thinking. reasoning_effort and thinking_budget cannot be set together, and Alibaba recommends reasoning_effort because enable_thinking will be deprecated."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"budget":{"min":0,"max":262144,"unit":"tokens"},"effort_options":["none","low","medium","xhigh"],"continuation":["thinking_blocks"],"notes":["Prefer reasoning_effort; none disables thinking. thinking_budget is an alternative control and must not be sent with effort.","Omitting both controls uses the API default; explicitly selecting xhigh maps to 262144 budget tokens, not the omitted budget default of 131072.","Set preserve_thinking=true to retain reasoning_content across turns."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"xhigh"}}},{"id":"qwen3.8-max","name":"Qwen3.8 Max","family":"qwen","display_name":"Qwen3.8 Max","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"toggle"},{"type":"budget"},{"type":"effort","values":["none","low","medium","xhigh"],"exclusive_with":["budget"]}],"last_updated":"2026-08-31","modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.17,"cache_write":2.5},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["multimodal","reasoning","coding"],"lifecycle":"active","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"standard","notes":["Thinking mode has a 983616-token input limit and a separate 262144-token reasoning budget.","Cache prices refer to explicit caching. Longer inputs may use higher pricing tiers.","reasoning_effort defaults to xhigh and accepts xhigh, medium, and low; max maps to xhigh, minimal maps to low, and none disables thinking. reasoning_effort and thinking_budget cannot be set together, and Alibaba recommends reasoning_effort because enable_thinking will be deprecated."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"budget":{"min":0,"max":262144,"unit":"tokens"},"effort_options":["none","low","medium","xhigh"],"continuation":["thinking_blocks"],"notes":["Prefer reasoning_effort; none disables thinking. thinking_budget is an alternative control and must not be sent with effort.","Omitting both controls uses the API default; explicitly selecting xhigh maps to 262144 budget tokens, not the omitted budget default of 131072.","Set preserve_thinking=true to retain reasoning_content across turns."],"interleaved":true,"summaries":true,"visibility":"summary","default_enabled":true,"mode":"effort","effort":"xhigh"}}},{"id":"qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","family":"qwen3.8-omni","display_name":"Qwen3.8 Omni Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"release_date":"2026-09-17","last_updated":"2026-09-17","open_weights":false,"modalities":{"input":["text","image","audio","video"],"output":["text"]},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"limit":{"context":1000000,"output":131072},"metadata":{"selection":["latest","multimodal","audio-video-understanding","reasoning"],"lifecycle":"active","pricingRegion":"Singapore","pricingScope":"International","pricingBasis":"standard","notes":["Accepts text, image, audio, and video input and returns text.","Model Studio API keys are region-specific; endpoint availability varies by region."],"sourceProvider":"qwen","sourceProviderName":"Qwen","sourceDocs":["https://www.alibabacloud.com/help/en/model-studio/models","https://www.alibabacloud.com/help/en/model-studio/model-pricing","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-omni-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen-omni","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-7-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-plus","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-flash","https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-coder-next","https://www.alibabacloud.com/help/en/model-studio/deep-thinking","https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions","https://www.alibabacloud.com/help/en/model-studio/qwen-function-calling","https://huggingface.co/Qwen/Qwen3-Coder-Next"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":["none","low","medium","xhigh"],"notes":["Default effort is xhigh. minimal maps to low; high and max map to xhigh. none disables thinking.","Do not combine reasoning_effort with thinking_budget."],"default_enabled":true,"mode":"effort","effort":"xhigh"}}},{"id":"step-3.5-flash","name":"Step 3.5 Flash","family":"step","display_name":"Step 3.5 Flash","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"limit":{"context":262144,"output":262144},"metadata":{"selection":["coding","reasoning","cost-efficient"],"lifecycle":"active","notes":["max_tokens is bounded by the shared input/output context window. Structured output support refers to JSON mode."],"sourceProvider":"stepfun","sourceProviderName":"StepFun","sourceDocs":["https://platform.stepfun.ai/docs/en/guides/models/step-5-preview","https://platform.stepfun.ai/docs/en/guides/models/step-3.7-flash","https://platform.stepfun.ai/docs/en/guides/models/step-3.5-flash","https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create","https://platform.stepfun.ai/docs/en/guides/developer/reasoning","https://platform.stepfun.ai/docs/en/guides/pricing/details","https://huggingface.co/stepfun-ai/Step-3.7-Flash"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","notes":["The API returns reasoning by default; reasoning_format=deepseek-style switches the response field to reasoning_content."]}}},{"id":"step-3.5-flash-2603","name":"Step 3.5 Flash 2603","family":"step","display_name":"Step 3.5 Flash 2603","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"last_updated":"2026-08-31","modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"limit":{"context":262144,"output":262144},"metadata":{"selection":["coding","reasoning","cost-efficient"],"lifecycle":"active","notes":["max_tokens is bounded by the shared input/output context window. Structured output support refers to JSON mode."],"sourceProvider":"stepfun","sourceProviderName":"StepFun","sourceDocs":["https://platform.stepfun.ai/docs/en/guides/models/step-5-preview","https://platform.stepfun.ai/docs/en/guides/models/step-3.7-flash","https://platform.stepfun.ai/docs/en/guides/models/step-3.5-flash","https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create","https://platform.stepfun.ai/docs/en/guides/developer/reasoning","https://platform.stepfun.ai/docs/en/guides/pricing/details","https://huggingface.co/stepfun-ai/Step-3.7-Flash"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high"],"notes":["The API returns reasoning by default; reasoning_format=deepseek-style switches the response field to reasoning_content."]}}},{"id":"step-3.7-flash","name":"Step 3.7 Flash","family":"step","display_name":"Step 3.7 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"last_updated":"2026-08-31","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"limit":{"context":262144,"output":262144},"metadata":{"selection":["latest","multimodal","coding","reasoning"],"lifecycle":"active","notes":["max_tokens is bounded by the shared input/output context window. Structured output support refers to JSON mode."],"sourceProvider":"stepfun","sourceProviderName":"StepFun","sourceDocs":["https://platform.stepfun.ai/docs/en/guides/models/step-5-preview","https://platform.stepfun.ai/docs/en/guides/models/step-3.7-flash","https://platform.stepfun.ai/docs/en/guides/models/step-3.5-flash","https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create","https://platform.stepfun.ai/docs/en/guides/developer/reasoning","https://platform.stepfun.ai/docs/en/guides/pricing/details","https://huggingface.co/stepfun-ai/Step-3.7-Flash"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"notes":["The API returns reasoning by default; reasoning_format=deepseek-style switches the response field to reasoning_content."]}}},{"id":"step-5-preview","name":"Step 5 Preview","family":"step","display_name":"Step 5 Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"structured_output":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"last_updated":"2026-09-20","modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":1,"output":2.7,"cache_read":0.05},"limit":{"context":1000000,"output":384000},"metadata":{"selection":["latest","frontier","multimodal","agentic","long-context"],"lifecycle":"preview","notes":["Official maximum input and output are both 1M tokens and max_tokens defaults to INF; 384000 is recorded as a conservative default output ceiling.","Cache-miss input billing includes writing new content to the cache; output tokens include both the reasoning process and the final answer."],"sourceProvider":"stepfun","sourceProviderName":"StepFun","sourceDocs":["https://platform.stepfun.ai/docs/en/guides/models/step-5-preview","https://platform.stepfun.ai/docs/en/guides/models/step-3.7-flash","https://platform.stepfun.ai/docs/en/guides/models/step-3.5-flash","https://platform.stepfun.ai/docs/en/api-reference/chat/chat-completion-create","https://platform.stepfun.ai/docs/en/guides/developer/reasoning","https://platform.stepfun.ai/docs/en/guides/pricing/details","https://huggingface.co/stepfun-ai/Step-3.7-Flash"],"sourceStatus":"seed","apiListed":false,"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"notes":["The API returns reasoning by default; reasoning_format=deepseek-style switches the response field to reasoning_content."]}}}],"metadata":{"catalogKind":"generated-fallback","fallbackPriority":"before-aihubmix","sourcePolicy":"official-api-plus-official-doc-derived-seeds","source":"public-provider-conf"}},"aihubmix":{"id":"aihubmix","name":"AIHubMix","display_name":"AIHubMix","updated_at":"2026-10-18T20:13:13.581Z","models":[{"id":"auto","name":"auto","display_name":"auto","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","audio","image","video"]},"cost":{"input":2,"output":2},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"AIHubMix Smart Router: Fill in the model name as auto, and the gateway will automatically select the optimal model based on the request content;\n\nThe auto without a suffix uses the default strategy cost_optimized. You can explicitly specify the focus using auto:<strategy>, such as auto (= auto:cost_optimized) cost priority: choose the cheapest as long as the capability meets the standard; auto:balanced balanced: considers capability / cost / latency\n\nauto:quality_first quality priority: prioritize selecting the strongest capability for complex reasoning and critical outputs\n\nauto:latency_critical low latency priority: prioritize selecting the fastest response","typeHints":["llm"],"features":["thinking","web","deepsearch","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","audio","image","video"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4.1-flash-1017","name":"deepseek-v4.1-flash-1017","display_name":"deepseek-v4.1-flash-1017","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.155,"output":0.62,"cache_read":0.0031},"limit":{"context":8192,"output":8192},"metadata":{"description":"The official latest version of DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. API usage and pricing remain unchanged—you can still access the latest model using deepseek-flash.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.0031,"input":0.155,"output":0.62},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6.1-sol","name":"gpt-6.1-sol","display_name":"gpt-6.1-sol","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":10,"cache_read":0.1},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-6.1 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex programming and agent workflows. GPT-6.1 Sol's performance in complex programming, computer operations, and professional work tasks is close to Astra, but at a lower cost. You can compare the two on your own tasks to weigh quality against cost.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.1,"cache_write":2.5,"input":2,"output":10,"tiers":[{"cache_read":0.2,"cache_write":5,"input":4,"output":15,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"jev-1.14","name":"jev-1.14","display_name":"jev-1.14","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.0462,"output":0},"limit":{"context":64000,"output":64000},"metadata":{"description":"Jev 1.14 is TypeSafe’s structured decision model for classification, scoring, and agent routing, returning typed results with calibrated probabilities. Compared with Jev 1.13, it brings improvements in multilingual support and adds experimental bounding-box outputs for images.","typeHints":["decision"],"inputModalities":["text","image"],"pricing":{"input":0.0462,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"muse-wonder","name":"muse-wonder","display_name":"muse-wonder","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":4.4,"output":22,"cache_read":0.22},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Muse Wonder is Meta’s model for complex coding, long-running agents, and computer use. With a 1M-token context window, it plans multi-step tasks, delegates to sub-agents, and combines Active Memory with Active Focus to retain relevant context and sustain progress on challenging tasks.","typeHints":["llm"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.22,"input":4.4,"output":22},"source":"public-provider-conf"},"vision":true},{"id":"gemini-4-argon","name":"gemini-4-argon","display_name":"gemini-4-argon","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":2,"output":10,"cache_read":0.1},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 4 Argon is Google DeepMind’s multimodal reasoning model for complex software engineering, financial research, legal drafting, and cybersecurity defense. It supports sustained reasoning across long, multi-step workflows, combining coding capabilities with chart and long-video understanding. It can also autonomously discover, validate, and patch software vulnerabilities.","typeHints":["llm"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.1,"input":2,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"gemini-nano-banana-2.1","name":"gemini-nano-banana-2.1","display_name":"gemini-nano-banana-2.1","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"limit":{"context":65536,"output":65536},"metadata":{"description":"Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) is Google's latest high-efficiency image generation and conversational editing model. As an upgraded version of Nano Banana 2 (Gemini 3.1 Flash Image), it significantly improves visual quality, prompt adherence, role consistency in multi-turn conversations, and text rendering while maintaining Flash-level speed and cost efficiency. It can be regarded as a more efficient counterpart to Gemini 3 Pro Image (Nano Banana Pro).","typeHints":["image_generation","llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.15,"input":1.5,"output":7.5},"source":"public-provider-conf"},"vision":true},{"id":"claude-haiku-5-5","name":"claude-haiku-5-5","display_name":"claude-haiku-5-5","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.1,"output":0.5,"cache_read":0.01},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Haiku 5.5 is Anthropic’s next-generation product, designed for high-throughput, cost-sensitive tasks. It can reliably handle fast and repetitive workloads such as summarization, context compression, database queries, and classification requests. It is also well suited to be used as a sub-agent model in programming workflows alongside Opus 5.5 and Sonnet 5.5.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.5,"tiers":[{"cache_read":0.05,"cache_write":0.625,"input":0.5,"output":2.5,"tier":{"size":100000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"qwen-image-2.1-pro","name":"qwen-image-2.1-pro","display_name":"qwen-image-2.1-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen-Image-2.1-Pro is a unified text-to-image generation and image-editing model in the Tongyi Qianwen (Qwen) series. Its visual generation component contains only 7 billion parameters (a 32-layer single-stream DiT), achieving a good balance between generation quality, inference efficiency, and versatility. This release includes four key improvements:\n- Compact and efficient: adopts a lightweight architecture that combines hybrid-granularity attention and prefix KV cache reuse to deliver high-quality image generation with low computational cost.\n- Native transparency support, unified generation and editing: can generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photos—all handled by a single model.\n- Versatile editing: supports up to 10 reference images, allows specifying local edit regions via circular or freehand annotations or separate masks, and preserves identity features of people and products.\n- Photorealistic textures and refined aesthetics: improved typography, portrait lighting, and detail rendering for more visually appealing results.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"qwen-image-2.1-turbo","name":"qwen-image-2.1-turbo","display_name":"qwen-image-2.1-turbo","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen-Image-2.1-Turbo is currently the best-balanced and most cost-effective open-source image generation model in the Qwen-Image series, offering four core advantages: a lightweight model with strong performance and excellent value; native transparency support with integrated generation and editing; flexible editing—supporting multiple reference images, local control, high-fidelity restoration, and comprehensive editing capabilities; and realistic textures, elegant typography, and refined portrait quality.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"qwen3.8-flash-free","name":"qwen3.8-flash-free","display_name":"qwen3.8-flash-free","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen3.8 Flash is available for free on AIHubMix as part of GMI Cloud’s promotional campaign. The offer lasts for 30 days from launch or until the campaign credits are exhausted, whichever comes first.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-max-free","name":"qwen3.8-max-free","display_name":"qwen3.8-max-free","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen3.8 Max is available for free on AIHubMix as part of GMI Cloud’s promotional campaign. The offer lasts for 30 days from launch or until the campaign credits are exhausted, whichever comes first.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-5-5","name":"claude-opus-5-5","display_name":"claude-opus-5-5","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","pdf"]},"cost":{"input":4,"output":20,"cache_read":0.2},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Opus 5.5 is Anthropic’s latest flagship model. In Anthropic’s comprehensive alignment testing, Opus 5.5 is the strongest-performing model tested to date. It also includes the safety safeguards Anthropic has developed for its most capable models.","typeHints":["llm"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.2,"cache_write":5,"input":4,"output":20},"source":"public-provider-conf"},"vision":true},{"id":"claude-sonnet-5-5","name":"claude-sonnet-5-5","display_name":"claude-sonnet-5-5","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2,"output":10,"cache_read":0.1},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Sonnet 5.5 is the next-generation product in Anthropic’s Sonnet model series; Claude Sonnet 5.5 offers the best balance between speed and intelligence. The following five major changes will affect code currently running on Claude Sonnet 5:\n1. Using \"between_tools\" can disable up-front thinking.\n2. Forcing the use of tools will result in an error.\n3. Thinking content blocks are bound to the model and the conversation.\n4. On the Claude API and Google Cloud, the older \"computer_20251124\" computer tool usage is no longer accepted.\n5. The advisor tool will refuse to accept Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisor models.\n\nUse between_tools to disable up-front thinking.\nForcing tool use will return an error.\nThinking blocks are bound to the model and the conversation.\nOn the Claude API and Google Cloud, early computer_20251124 computer tool usage is no longer accepted.\nThe advisor tool no longer accepts Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors.","typeHints":["llm"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.1,"cache_write":2.5,"input":2,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6-luna","name":"gpt-6-luna","display_name":"gpt-6-luna","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.1,"output":0.5,"cache_read":0.01},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-6 Luna is OpenAI's latest and most efficient model, designed for focused, high-throughput tasks.","typeHints":["llm","decision"],"inputModalities":["text","image"],"pricing":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.5,"tiers":[{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":0.75,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6-sol","name":"gpt-6-sol","display_name":"gpt-6-sol","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":10,"cache_read":0.2},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-6 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex programming and agent workflows.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":15,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"mistral-large-4-0","name":"mistral-large-4-0","display_name":"mistral-large-4-0","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.36,"output":4.17996,"cache_read":0.139944},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Mistral Large 4 is Mistral AI’s frontier multimodal model with text and image input, designed for complex reasoning, coding, and agentic workflows. It supports tool calling and structured outputs, with a 512K-token context window and up to 256K output tokens, making it well suited for long-context and multi-step tasks. Compared with earlier Mistral large models, Mistral Large 4 places greater emphasis on multimodal understanding, extended context, and agentic execution.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.139944,"input":1.36,"output":4.17996},"source":"public-provider-conf"},"vision":true},{"id":"grok-4.7","name":"grok-4.7","display_name":"grok-4.7","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.5},"limit":{"context":500000,"output":500000},"metadata":{"description":"Grok 4.7 is xAI’s flagship model for coding, agentic tasks, and professional knowledge work. Compared with Grok 4.6, it uses a larger base model and longer reinforcement-learning training, improving long-horizon task execution, self-verification, context management, and document and presentation creation.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.5,"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"mimo-v2.6-flash","name":"mimo-v2.6-flash","display_name":"mimo-v2.6-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.155,"output":0.31,"cache_read":0.0031},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"mimo-v2.6-flash is Xiaomi's latest model series. A fully multimodal, highly intelligent, low-cost efficient inference model, it is the best-balanced choice for high-frequency invocations and large-scale tasks in professional office settings.","typeHints":["llm"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.0031,"input":0.155,"output":0.31},"source":"public-provider-conf"},"vision":true},{"id":"mimo-v2.6-pro","name":"mimo-v2.6-pro","display_name":"mimo-v2.6-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.48,"output":0.96,"cache_read":0.00384},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"MiMo-V2.6-Pro is Xiaomi’s trillion-parameter, natively omni-modal flagship reasoning model for complex projects, long-horizon agentic tasks, coding, research, and professional knowledge work. It supports a 1M-token context window and up to 128K output tokens. Compared with V2.5, it delivers stronger reasoning and long-task performance while retaining the same API pricing.","typeHints":["llm"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.00384,"input":0.48,"output":0.96},"source":"public-provider-conf"},"vision":true},{"id":"mimo-v2.6-pro-ultraspeed","name":"mimo-v2.6-pro-ultraspeed","display_name":"mimo-v2.6-pro-ultraspeed","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":4.8,"output":9.6,"cache_read":0.0384},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"MiMo-V2.6-Pro-UltraSpeed combines the flagship performance of MiMo-V2.6-Pro and offers up to 20× output speed to serve highly real-time interactive and latency-sensitive production scenarios.","typeHints":["llm"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.0384,"input":4.8,"output":9.6},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.8-flash-lite-tts","name":"gemini-3.8-flash-lite-tts","display_name":"gemini-3.8-flash-lite-tts","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.5,"output":6,"cache_read":0.125},"limit":{"context":8192,"output":16384},"metadata":{"description":"Gemini 3.8 Flash-Lite TTS (gemini-3.8-flash-lite-tts) is Google's fast, cost-efficient workhorse text-to-speech model, built to replace gemini-3.1-flash-tts-preview for high-throughput production workloads.","typeHints":["tts"],"inputModalities":["text"],"pricing":{"cache_read":0.125,"input":0.5,"output":6},"source":"public-provider-conf"},"vision":false},{"id":"gemini-3.8-flash-tts","name":"gemini-3.8-flash-tts","display_name":"gemini-3.8-flash-tts","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.5,"output":9,"cache_read":0.125},"limit":{"context":8192,"output":16384},"metadata":{"description":"Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) is Google's 3.8 Flash text-to-speech audio model, designed to deliver studio-grade sound fidelity, expressive performance, and long-form stability.","typeHints":["tts"],"inputModalities":["text"],"pricing":{"cache_read":0.125,"input":0.5,"output":9},"source":"public-provider-conf"},"vision":false},{"id":"qwen3.8-omni-flash","name":"qwen3.8-omni-flash","display_name":"qwen3.8-omni-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","audio","video"]},"cost":{"input":0.1126,"output":0.380025,"cache_read":0.014075},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen3.8 Omni Flash is Alibaba Cloud Qwen's next-generation native multimodal model, supporting 1M-length sequences and able to directly accept text, images, audio, and video as input. It is based on the Qwen3.8-Flash-Next architecture. The model is designed for agent capabilities in real productivity scenarios: while offering agentic abilities such as programming, text knowledge work, and GUI operation, it also achieves significant results in audio/video-centered agentic applications—such as video editing, music video creation, film production and narration, audio/video-to-text-and-image summarization, and audio/video dialogue—that require integrated processing of text, images, audio, and video. It supports 2-channel and 4-channel spatial audio parsing, is compatible with DashScope and OpenAI protocols, and it is recommended to install the accompanying Qwen-MM-Plugins to facilitate agent frameworks' access to native multimodal capabilities.","typeHints":["llm"],"inputModalities":["text","image","audio","video"],"pricing":{"cache_read":0.014075,"cache_write":0.175937,"input":0.1126,"output":0.380025},"source":"public-provider-conf"},"vision":true},{"id":"jev-1.13","name":"jev-1.13","display_name":"jev-1.13","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.0462,"output":0},"limit":{"context":64000,"output":64000},"metadata":{"description":"Jev is a structured decision model launched by TypeSafe and is also their first \"System One\" model.\n\nSystem One models can make structured decisions for software quickly, returning typed selection results rather than freely generated text. They are suitable for routing, classification, and other decision nodes in applications—where fast, predictable answers are more important than generating natural language content.","typeHints":["decision"],"inputModalities":["text","image"],"pricing":{"input":0.0462,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"jev-latest","name":"jev-latest","display_name":"jev-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.0462,"output":0},"limit":{"context":64000,"output":64000},"metadata":{"description":"Jev is a structured decision model launched by TypeSafe and is also their first \"System One\" model.\n\nSystem One models can make structured decisions for software quickly, returning typed selection results rather than freely generated text. They are suitable for routing, classification, and other decision nodes in applications—where fast, predictable answers are more important than generating natural language content.","typeHints":["decision"],"inputModalities":["text","image"],"pricing":{"input":0.0462,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"decision-model-preview","name":"decision-model-preview","display_name":"decision-model-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":64000,"output":64000},"metadata":{"description":"Alibaba Cloud has launched the decision model decision-model-preview. This structured decision model is designed for high-frequency business judgments; it can concurrently perform classification, binary decisions, and scoring based on text or business state, and returns probability distributions and confidence levels. It is suitable for scenarios such as ticket routing, content moderation, agent routing, and result verification. Free for a limited time.","typeHints":["decision"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"step-5-preview","name":"step-5-preview","display_name":"step-5-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":1.08,"output":3.0888,"cache_read":0.054},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Step 5 Preview is StepFun's next-generation flagship base model designed for real-world tasks, with a focus on programming and professional expertise.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.054,"input":1.08,"output":3.0888},"source":"public-provider-conf"},"vision":true},{"id":"doubao-seedream-5-0-flash","name":"doubao-seedream-5-0-flash","display_name":"doubao-seedream-5-0-flash","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-Seedream-5.0-flash is a fast image-creation model released by ByteDance that balances speed and cost efficiency; it supports precise editing, layer separation, and transparent-background output, making it suitable for high-frequency, large-scale image production and rapid interactive scenarios.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"glm-5.3-flashx","name":"glm-5.3-flashx","display_name":"glm-5.3-flashx","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.282,"output":0.987,"cache_read":0.08037},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"GLM-5.3-FlashX is Z.AI’s high-speed inference model, designed for coding agents, real-time interactions, long-running agentic workflows, and applications that require fast token generation. It is heavily optimized at the inference infrastructure level for lower latency and higher execution efficiency, reaching generation speeds of up to 200 tokens per second. Compared with GLM-5.3-Flash, GLM-5.3-FlashX delivers up to 5× faster inference, with a stronger focus on low-latency and high-throughput workloads.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.08037,"input":0.282,"output":0.987},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6-astra","name":"gpt-6-astra","display_name":"gpt-6-astra","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":10,"output":50,"cache_read":1},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-6 Astra is OpenAI's newest and most intelligent model, with industry-leading performance in computer operations, web browsing, software engineering, scientific research, and professional work. It excels at executing multi-step workflows across code, browsers, and various professional software. Astra can achieve better results with significantly fewer output tokens, making its estimated API cost per task lower.","typeHints":["llm"],"features":["tools","thinking","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":1,"cache_write":12.5,"input":10,"output":50,"tiers":[{"cache_read":2,"cache_write":25,"input":20,"output":75,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"jina-ocr-v1","name":"jina-ocr-v1","display_name":"jina-ocr-v1","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image"]},"cost":{"input":0,"output":0},"limit":{"context":32000,"output":32000},"metadata":{"description":"jina-ocr-v1 is Jina AI's latest page-to-Markdown document parsing model, with 570 million active parameters. Its architecture inherits the DeepEncoder from DeepSeek-OCR; jina-ocr-v1 retains that encoder and decoder, and thus supports document parsing for approximately 100 languages.(This model is free for a limited time.)","typeHints":["ocr"],"inputModalities":["image"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.8-flash","name":"gemini-3.8-flash","display_name":"gemini-3.8-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 3.8 Flash is Google's most intelligent Flash-series model, designed for long-running software engineering tasks, autonomous agents, and complex enterprise workflows, while retaining the Flash series' fast responsiveness and cost-effectiveness.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"deepseek-v4.1-flash","name":"deepseek-v4.1-flash","display_name":"deepseek-v4.1-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.1408,"output":0.5632,"cache_read":0.002816},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"DeepSeek-V4.1-Flash model official release. This is the smallest model in DeepSeek’s new model-architecture series, featuring native multimodal visual understanding capabilities. The new architecture is designed to deliver a higher capability ceiling, faster inference speeds, greater throughput, and scalability to larger-parameter models.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.002816,"input":0.1408,"output":0.5632},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.3-flash","name":"glm-5.3-flash","display_name":"glm-5.3-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.11268,"output":0.39438,"cache_read":0.032396},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"GLM-5.3-Flash is a high-efficiency multimodal model from Z.AI. It supports a context window of roughly 1 million tokens, along with text, image, and video inputs, and includes tool-calling capabilities. It is primarily designed for coding agents, complex reasoning, and long-horizon software engineering tasks. Built on the existing GLM technology stack, the model has been further post-trained and optimized to deliver strong performance while placing greater emphasis on inference efficiency, responsiveness, and cost.The model is offered at a limited-time 50% discount; users are welcome to try it.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.032396,"input":0.11268,"output":0.39438},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xiaomi-mimo-v2.6-pro-free","name":"xiaomi-mimo-v2.6-pro-free","display_name":"xiaomi-mimo-v2.6-pro-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"xiaomi-mimo-v2.6-pro-free is the open free version of xiaomi-mimo-v2.6-pro.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"inputModalities":["text","image","video","audio"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"claude-fable-5-1","name":"claude-fable-5-1","display_name":"claude-fable-5-1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":11,"output":55,"cache_read":0.275},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude-fable-5-1 is Anthropic's most capable newly released model, suitable for the most demanding reasoning and long-running agent work. Claude Fable 5.1, while keeping input and output prices the same as Claude Fable 5, reduces cache read prices to one quarter of the original and is more capable for long-running agent programming, multi-step research, and document, spreadsheet, and slide processing. (The model is extremely expensive and not recommended for casual use.)","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.275,"cache_write":13.75,"input":11,"output":55},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"gpt-live-transcribe","name":"gpt-live-transcribe","display_name":"gpt-live-transcribe","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio","text"]},"cost":{"input":0,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"OpenAI's latest realtime speech-to-text model, built for low-latency use — it streams incremental transcripts as audio arrives, ideal for live captions, dictation, and voice interfaces. Supports automatic transcription across 57 languages, with keyword/context hints and a tunable latency-vs-accuracy tradeoff.","typeHints":["stt"],"inputModalities":["audio","text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"gpt-realtime-2.1","name":"gpt-realtime-2.1","display_name":"gpt-realtime-2.1","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","audio","image"]},"cost":{"input":4,"output":24,"cache_read":0.4},"limit":{"context":128000,"output":128000},"metadata":{"description":"GPT-Realtime-2.1 is a reasoning speech-to-speech model for the Realtime API, with tool use and configurable reasoning effort, improving on GPT-Realtime-2 in alphanumeric recognition, silence and noise handling, and interruption behavior.","typeHints":["tts","stt"],"inputModalities":["text","audio","image"],"pricing":{"cache_read":0.4,"input":4,"output":24},"source":"public-provider-conf"},"vision":true},{"id":"qwen-3.8-27b","name":"qwen-3.8-27b","display_name":"qwen-3.8-27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":1.1,"output":1.65},"limit":{"context":131072,"output":131072},"metadata":{"description":"Qwen3.8-27b is an Alibaba-released dense vision-language model with open-source weights. Qwen3.8 was developed based on the architecture of Qwen3.5, achieving significant improvements in encoding capability, handling professional tasks, research tasks, and tasks that require long-term completion. Qwen3.8-27B integrates these advantages into a compact, easy-to-deploy dense model — a native vision-language model capable of understanding image and video information and featuring flexible cognitive control capabilities. This model can more reliably accomplish complex, multi-step tasks.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"input":1.1,"output":1.65},"source":"public-provider-conf"},"vision":true},{"id":"glm-5.3","name":"glm-5.3","display_name":"glm-5.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.1268,"output":3.9438,"cache_read":0.2817},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"GLM-5.3 is Z.AI’s coding and agentic reasoning model, built for complex software engineering, long-running agent tasks, vulnerability analysis, and other demanding workloads. Building on GLM-5.2, it incorporates further post-training improvements to deliver stronger coding performance, better task execution, and greater token efficiency.\n\nWe currently offer the production-ready GLM-5.3 API with unlimited concurrency, making it well suited for high-throughput workloads, coding agents, and large-scale automation. For a limited time, GLM-5.3 is available at 10% off.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.2817,"input":1.1268,"output":3.9438},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-image-2.5-flare","name":"gpt-image-2.5-flare","display_name":"gpt-image-2.5-flare","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":30,"cache_read":1.25},"limit":{"context":8192,"output":8192},"metadata":{"description":"GPT-Image-2.5 Flare is OpenAI's latest image model, the fastest and suited for everyday high-quality image generation. It accepts text and image inputs and produces image outputs. The model supports quality settings: low, medium, high, xhigh, max, and auto.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"cache_read":1.25,"input":5,"output":30},"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-2.5-sunburst","name":"gpt-image-2.5-sunburst","display_name":"gpt-image-2.5-sunburst","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":30,"cache_read":1.25},"limit":{"context":8192,"output":8192},"metadata":{"description":"GPT Image 2.5 Sunburst is OpenAI's latest image model, capable of generating and editing images from text and image inputs. It is suitable for workflows that require extremely high editing precision. The model supports quality settings: low, medium, high, xhigh, max, and auto.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"cache_read":1.25,"input":5,"output":30},"source":"public-provider-conf"},"vision":true},{"id":"mercury-2.5-preview","name":"mercury-2.5-preview","display_name":"mercury-2.5-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.75,"cache_read":0.02},"limit":{"context":260000,"output":260000},"metadata":{"description":"Mercury 2.5 is the latest diffusion-based large language model (dLLM) released by Inception. It is the fastest inference LLM; unlike the sequential token-by-token generation approach, Mercury 2.5 can generate and optimize multiple tokens in parallel, achieving a generation speed of 1,107 tokens per second on standard GPUs. Compared to Mercury 2, its intelligence has increased by more than 10 percentage points, and its quality rivals leading cost-optimized frontier models such as GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5.","typeHints":["llm"],"features":["thinking","tools"],"inputModalities":["text"],"pricing":{"cache_read":0.02,"input":0.2,"output":0.75},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-max-2026-09-02","name":"qwen3.8-max-2026-09-02","display_name":"qwen3.8-max-2026-09-02","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":1.69,"output":5.07,"cache_read":0.169},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen3.8-Max-0902 (also known as qwen3.8-max-2026-09-02) is a snapshot version of Alibaba Cloud Tongyi Qianwen's qwen3.8-max. It pushes encoding depth further, enabling it to handle more complex engineering-level projects and long-term autonomous development; collaborative agent capabilities are significantly enhanced, performing more confidently in multi-tool orchestration and end-to-end delivery; visual understanding is comprehensively improved, with more sensitive and accurate chart reasoning, document parsing, and multimodal perception. Continuing the 1-million-context window, reasoning modes, and a complete tool ecosystem, it continues to evolve at a higher level of intelligence.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.169,"cache_write":2.1125,"input":1.69,"output":5.07},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"hy4-preview","name":"hy4-preview","display_name":"hy4-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.845,"output":2.535,"cache_read":0.04225},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Hy4 Preview is Tencent Hunyuan’s large language model for agents, coding, office automation, and complex tool use.Hy4 preview has a total of 770B parameters and 49B active parameters, and is primarily optimized for agent, coding, and productivity scenarios. It strengthens understanding, planning, tool invocation, and sustained execution capabilities for complex tasks. Compared with the previous generation, Hy4 preview further improves multi-step agents, code development, and productivity tasks, offering better task decomposition, context continuity, instruction following, and long-horizon execution. In coding scenarios, it further enhances code understanding, generation, modification, and the handling of complex engineering tasks; in productivity scenarios, it focuses on improving document processing, information analysis, office automation, game development, webpage generation, and cross-tool collaboration. Hy4 preview is suitable for coding agents, complex tool invocation, and various agent workflows that require multi-step planning and sustained execution, providing more reliable task completion for complex real-world business scenarios.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.04225,"input":0.845,"output":2.535},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5.3","name":"coding-glm-5.3","display_name":"coding-glm-5.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22,"cache_read":0.015},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"GLM-5.3 is Z.ai’s reasoning model for coding and agentic workflows, designed for complex software engineering, long-running agents, and vulnerability analysis. It uses the same base model as GLM-5.2, with scaled post-training improving coding, task execution, and token efficiency.\n\nThis model is a limited-time preview version of GLM-5.3, intended for testing and evaluation only. Service stability is not guaranteed, and we do not recommend using it in production environments. We’re waiting for the official commercial API release and will integrate it as soon as official support becomes available.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.015,"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5.3-flash-free","name":"coding-glm-5.3-flash-free","display_name":"coding-glm-5.3-flash-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0,"output":0},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"coding-glm-5.3-flash-free is the open and free version of coding-glm-5.3-flash. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5.3-flash","name":"coding-glm-5.3-flash","display_name":"coding-glm-5.3-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.02817,"output":0.098595,"cache_read":0.007043},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Coding GLM 5.3 Flash is a dedicated version of GLM 5.3 Flash built for AI coding and Coding Agent workflows. It is designed for code understanding, generation, editing, repository-level development, and automated software engineering tasks. With support for context windows of up to approximately 1 million tokens, it can handle large codebases and extended development sessions. The model also supports text, image, and video inputs, along with tool use, making it well suited for AI coding tools such as Claude Code, OpenCode, Cline, and other agentic development environments.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.007043,"input":0.02817,"output":0.098595},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5.3-free","name":"coding-glm-5.3-free","display_name":"coding-glm-5.3-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"coding-glm-5.3-free is the open and free version of coding-glm-5.3. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.3","name":"muse-spark-1.3","display_name":"muse-spark-1.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":1.375,"output":4.675,"cache_read":0.165},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Muse Spark 1.3 is Meta’s multimodal reasoning model, designed for long-running agentic, multi-agent, and complex coding workflows. It can maintain context and task constraints across extended workflows, reconcile conflicting information, and request clarification or confirmation when needed. Compared with Muse Spark 1.2, Muse Spark 1.3 improves efficiency across long-horizon agentic and coding tasks, with fewer unnecessary turns, tool calls, and tokens, while producing more concise outputs.","typeHints":["llm"],"features":["thinking","tools"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.165,"input":1.375,"output":4.675},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-flash","name":"qwen3.8-flash","display_name":"qwen3.8-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.1126,"output":0.380025,"cache_read":0.014075},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen3.8 Flash is Alibaba Cloud Qwen’s flagship native vision-language model for coding, office tasks, long-context reasoning, and agent workflows. It supports a 1M-token context, 128K output, web access, and tool calling. Compared with Qwen3.7-Plus, Qwen3.8-Flash significantly reduces training and inference costs—the training overhead is only about one-ninth of the former—while offering stronger capabilities on coding and office tasks.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.014075,"cache_write":0.175937,"input":0.1126,"output":0.380025},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xiaomi-mimo-v2.6-flash-free","name":"xiaomi-mimo-v2.6-flash-free","display_name":"xiaomi-mimo-v2.6-flash-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"xiaomi-mimo-v2.6-flash-free is the open free version of xiaomi-mimo-v2.6-flash.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"inputModalities":["text","image","video","audio"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"mai-image-2.6","name":"mai-image-2.6","display_name":"mai-image-2.6","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":5},"limit":{"context":32000,"output":32000},"metadata":{"description":"MAI-Image-2.6 is Microsoft's latest image-generation and editing model. It can generate images from text prompts and supports image-guided editing in multiple aspect ratios.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":5,"output":5},"source":"public-provider-conf"},"vision":true},{"id":"mai-image-2.6-flash","name":"mai-image-2.6-flash","display_name":"mai-image-2.6-flash","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.75,"output":1.75},"limit":{"context":32000,"output":32000},"metadata":{"description":"MAI-Image-2.6 Flash is Microsoft’s low-latency version of the latest image model MAI-Image-2.6. It supports image generation in multiple aspect ratios and image-guided editing.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":1.75,"output":1.75},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.7-flash","name":"gemini-3.7-flash","display_name":"gemini-3.7-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"(This model has been officially taken offline; requests to gemini-3.5-flash will now be automatically routed to gemini-3.8-flash.)Gemini 3.7 Flash is Google’s natively multimodal reasoning model for coding, agents, web development, and knowledge work. It supports a 1M-token context window and adjustable thinking levels. Compared with Gemini 3.6 Flash, it improves coding, tool use, multi-step planning, and instruction following.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"minimax-h3-max","name":"minimax-h3-max","display_name":"minimax-h3-max","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"description":"MiniMax H3 (minimax-h3) is a general-purpose omni-modal generation model developed by the Chinese AI company MiniMax. It can jointly understand text, images, video, and audio while generating videos of up to 15 seconds in 2K resolution with native stereo sound. It is designed for advertising, branding, e-commerce, product design, UI/UX, and gaming. Compared with Hailuo 01 and Hailuo 02, H3 evolves from specialized video generation into a unified model for multimodal creation, reference-based editing, text rendering, and motion transfer.","typeHints":["video"],"inputModalities":["text","image"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":true},{"id":"agnes-3.0-flash","name":"agnes-3.0-flash","display_name":"agnes-3.0-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.03,"output":0.15},"limit":{"context":512000,"output":512000},"metadata":{"description":"Agnes 3.0 Flash is designed for real-world agent tasks and development workflows, covering the full execution chain from task understanding and planning to tool invocation and final delivery. The model focuses on improving stability, instruction-following, factual grounding, and output completeness in complex tasks, helping developers build more reliable agent applications.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"input":0.03,"output":0.15},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"agents-a1-free","name":"agents-a1-free","display_name":"agents-a1-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"Agents-A1 is a 35B Mixture-of-Experts (MoE) agentic model developed by InternScience for complex, long-horizon tasks across search, engineering, scientific research, instruction following, and tool use. The model is trained to scale both long-horizon agent trajectories and heterogeneous agent capabilities through a multi-stage training framework that combines full-domain supervised fine-tuning, domain-specialized teacher models, and multi-teacher on-policy distillation. Agents-A1 supports both text and image inputs and is designed for general-purpose agent workflows that require multi-step reasoning, planning, tool interaction, and sustained task execution.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"glm-5.2","name":"glm-5.2","display_name":"glm-5.2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.1268,"output":3.9438,"cache_read":0.2817},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow engineering standards more consistently, and complete the full development workflow from requirements to multi-platform deployment in a single task.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.2817,"input":1.1268,"output":3.9438},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"union-alpha-free","name":"union-alpha-free","display_name":"union-alpha-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"Developed by Stealth, Union Alpha is a multimodal model built for research, coding, and agentic workflows. It delivers frontier-level performance across a broad range of general-purpose tasks. Featuring a massive 262,144 token context window, this model is highly capable of handling extensive and complex tasks.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"intern-s2-free","name":"intern-s2-free","display_name":"intern-s2-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"Intern-S2-Preview is InternLM’s 35B scientific multimodal foundation model, designed for professional scientific reasoning, research agents, multimodal understanding, and complex scientific workflows. It scales the difficulty, diversity, and coverage of scientific tasks across the full training pipeline, while strengthening scientific agent capabilities, time-series modeling, molecular and material structure understanding, and efficient reasoning. Compared with the trillion-parameter Intern-S1-Pro, Intern-S2-Preview achieves comparable performance on multiple core scientific tasks with only 35B parameters, while retaining strong general reasoning and multimodal capabilities.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"deepseek-v4-flash-0731","name":"deepseek-v4-flash-0731","display_name":"deepseek-v4-flash-0731","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.142,"output":0.284,"cache_read":0.0284},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model developed by the Chinese AI company DeepSeek, with support for a million-token context window. It is designed for coding, complex reasoning, tool use, agentic workflows, and long-document processing. Its advantages include strong performance with fewer active parameters and improved efficiency through DSpark speculative decoding. Compared with DeepSeek V4-Flash Preview, it offers significantly stronger coding and agent capabilities, while outperforming DeepSeek V4-Pro Preview on several benchmarks with fewer active parameters.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.0284,"input":0.142,"output":0.284},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash-vision-exp","name":"deepseek-v4-flash-vision-exp","display_name":"deepseek-v4-flash-vision-exp","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.155,"output":0.62,"cache_read":0.0031},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"DeepSeek’s officially released new multimodal visual-understanding model, DeepSeek‑V4‑Flash‑Vision‑Exp, is experimental in nature and supports multimodal inputs. In pure-text capabilities (agents, reasoning, world knowledge, etc.), DeepSeek‑V4‑Flash‑Vision‑Exp is on par with the official DeepSeek‑V4‑Flash release.(The model name deepseek-v4-flash-vision-exp remains callable, but the official corresponding model has been taken offline; requests will be served by the DeepSeek-V4.1-Flash model and billed at Flash pricing.)","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.0031,"input":0.155,"output":0.62},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-v4-pro-0813","name":"deepseek-v4-pro-0813","display_name":"deepseek-v4-pro-0813","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.6918,"output":2.0754,"cache_read":0.023058},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"DeepSeek V4 Pro 0813 is DeepSeek’s high-performance general-purpose reasoning and agent model, designed for complex reasoning, coding, long-document analysis, and agentic workflows. It supports thinking and non-thinking modes, a 1M-token context window, up to 384K output, tool calling, and the Responses API. Compared with V4 Flash 0731, Pro prioritizes capability on complex tasks, while Flash focuses on speed, cost efficiency, and high concurrency.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.023058,"input":0.6918,"output":2.0754},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"dots-3-note-preview-free","name":"dots-3-note-preview-free","display_name":"dots-3-note-preview-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0,"output":0},"limit":{"context":524288,"output":524288},"metadata":{"description":"Dots3-Note Preview is an open-weight mixture-of-experts model developed by Dots Studio, featuring 16B active parameters out of 280B total. As the lightest model in the Dots 3 family, it is designed for efficient performance while supporting an expansive context length of 512,000 tokens. This preview version provides an accessible way to experience the capabilities of the Dots 3 architecture.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text","image","video","audio"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.6","name":"grok-4.6","display_name":"grok-4.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.5},"limit":{"context":500000,"output":500000},"metadata":{"description":"Grok 4.6 is xAI’s (SpaceXAI) flagship multimodal reasoning model for coding, long-running agents, knowledge work, and interactive application development. It supports image understanding, a 500K context window, tool calling, and structured outputs. Compared with Grok 4.5, it offers stronger multi-step execution, self-verification, coding, and visual project generation.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.5,"input":2,"output":6,"tiers":[{"cache_read":1,"input":4,"output":12,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"hy3-free","name":"hy3-free","display_name":"hy3-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":256000,"output":256000},"metadata":{"description":"The Hy3 official version is honed for real-world business scenarios, using a Mixture-of-Experts (MoE) architecture with 295B total parameters and 21B activated parameters. It natively supports a 256K context window and offers multiple thinking modes: no_think (ultra-fast response), think_low (quick thinking), and think_high (deep reasoning), balancing ultra-fast responses, complex reasoning, and invocation cost. Compared with the Preview version, Hy3—based on real business feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and others—focuses on improving the Coding Agent, long-form understanding, multi-turn context continuity, search QA, and complex task execution, performing more stably in reducing hallucinations, improving task completion, and engineering usability. It is better suited to practical scenarios such as frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step Agent workflows.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2.7-free","name":"minimax-m2.7-free","display_name":"minimax-m2.7-free","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":204800,"output":204800},"metadata":{"description":"Developed by Minimax, MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Featuring a generous 196,608-token context window, the model integrates advanced agentic capabilities through multi-agent workflows. It is uniquely built to actively participate in its own evolution, delivering highly adaptable and intelligent performance.","typeHints":["llm"],"features":["reasoning","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash-0731-fast","name":"deepseek-v4-flash-0731-fast","display_name":"deepseek-v4-flash-0731-fast","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.28,"output":1.4,"cache_read":0.07},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"DeepSeek V4 Flash 0731 Fast is a high-speed deployment of DeepSeek’s agentic model provided by Wafer, designed for coding, tool use, and high-volume agent workloads. It preserves the capabilities of V4 Flash 0731 while delivering much faster inference. Compared with V4 Pro, it prioritizes latency and execution efficiency.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.07,"input":0.28,"output":1.4},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mai-thinking-1","name":"mai-thinking-1","display_name":"mai-thinking-1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":2,"output":8},"limit":{"context":256000,"output":256000},"metadata":{"description":"MAI-Thinking-1 is Microsoft’s first inference model in the MAI series, built for enterprise-scale workloads. With excellent reasoning, mathematical, and general intelligence capabilities, combined with superior cost-effectiveness, it makes high-throughput, 24/7 AI workloads economically viable.","typeHints":["llm"],"features":["thinking","structured_outputs"],"inputModalities":["text"],"pricing":{"input":2,"output":8},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-xiaomi-mimo-v2.6-flash","name":"coding-xiaomi-mimo-v2.6-flash","display_name":"coding-xiaomi-mimo-v2.6-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.08,"output":0.16,"cache_read":0.0016},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.0016,"input":0.08,"output":0.16},"source":"public-provider-conf"},"vision":true},{"id":"wan3.0-video","name":"wan3.0-video","display_name":"wan3.0-video","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio","document","link"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wan 3.0 (Tongyi Wanxiang 3.0) is an integrated video generation and editing model launched by Alibaba’s Tongyi Lab. It is suitable for scenarios such as advertising, e-commerce, short films, character animation, video editing, and document-to-video. Its advantages include native support for videos up to 30 seconds long and the unified handling of reference content such as text, images, audio, video, documents, spreadsheets, presentations, and web pages, delivering more realistic visuals and audio, stable character consistency, and capabilities for referencing, editing, replication, and driving. Compared with Wan 2.7, which split text-to-video, image-to-video, reference generation, and editing across multiple models, Wan 3.0 integrates these capabilities into a single model, making the creative workflow more unified and flexible.","typeHints":["video"],"inputModalities":["text","image","video","audio","document","link"],"source":"public-provider-conf"},"vision":true},{"id":"wan3.0-video-prime","name":"wan3.0-video-prime","display_name":"wan3.0-video-prime","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio","document","link"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wan3.0 Video Prime is Alibaba Cloud’s preview high-speed edition of its All-in-One video model, positioned for faster-turnaround ads, ecommerce, short films, and editing. Aligned with Wan3.0 Video’s capabilities, it supports text-to-video, image-to-video, reference-based generation, document/webpage-to-video, up to 30 seconds at 30fps, 1080P output, adaptive aspect ratios, and native audio. It unifies modes that Wan 2.7 handled through separate task-specific models.","typeHints":["video"],"inputModalities":["text","image","video","audio","document","link"],"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.6-sol-disc","name":"gpt-5.6-sol-disc","display_name":"gpt-5.6-sol-disc","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":4,"output":20,"cache_read":0.4},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-5.6 Sol (limited-time 50% off) is OpenAI’s frontier reasoning model for complex coding, professional knowledge work, deep research, and long-running agents. It supports a roughly 1.05M-token context window, image understanding, and extensive tool use. Compared with Terra and Luna, Sol prioritizes capability and reliability on demanding tasks.","typeHints":["llm"],"features":["tools","thinking","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.4,"cache_write":5,"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seedance-2-5-260628","name":"doubao-seedance-2-5-260628","display_name":"doubao-seedance-2-5-260628","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":2,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedance 2.5 is ByteDance Seed’s next-generation unified multimodal audio-video generation model, designed for filmmaking, advertising, education, simulation, and long-form content creation. It generates up to 30 seconds of synchronized audio and video in one pass and supports multi-round extensions. Compared with Seedance 2.0, it offers stronger storytelling, smoother transitions, richer reference support, improved realism, and more precise editing.","typeHints":["video"],"inputModalities":["text","image","video","audio"],"pricing":{"input":2,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.6-luna","name":"gpt-5.6-luna","display_name":"gpt-5.6-luna","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":1.2,"cache_read":0.02},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families.","typeHints":["llm"],"features":["tools","thinking","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2,"tiers":[{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":1.8,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-sol","name":"gpt-5.6-sol","display_name":"gpt-5.6-sol","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":4,"output":20,"cache_read":0.4},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT‑5.6 Sol sets a new standard for both intelligence and efficiency, achieving state-of-the-art results across coding, knowledge work, cybersecurity, and science while outperforming previous and competing frontier models with fewer tokens and at lower estimated cost.","typeHints":["llm"],"features":["tools","thinking","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.4,"cache_write":5,"input":4,"output":20,"tiers":[{"cache_read":0.8,"cache_write":10,"input":8,"output":30,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-terra","name":"gpt-5.6-terra","display_name":"gpt-5.6-terra","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":12,"cache_read":0.2},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-5.6 Terra is designed for workloads that balance intelligence and cost. It roughly corresponds to the mini model tier used in earlier GPT-5 families.","typeHints":["llm"],"features":["tools","thinking","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12,"tiers":[{"cache_read":0.4,"cache_write":5,"input":4,"output":18,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.8-max","name":"qwen3.8-max","display_name":"qwen3.8-max","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":1.69,"output":5.07,"cache_read":0.169},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen3.8-Max is Alibaba Cloud Tongyi Qianwen's next-generation flagship large language model, featuring a mixture-of-experts (MoE) architecture with 2.4 trillion parameters. It achieves another breakthrough in encoding depth, enabling it to handle more complex engineering-grade projects and long-term autonomous development; collaborative agent capabilities are significantly enhanced, performing more confidently in multi-tool orchestration and end-to-end delivery; visual understanding is comprehensively improved, with more sensitive and accurate chart reasoning, document parsing, and multimodal perception. Continuing the 1-million-context window, reasoning modes, and a complete tool ecosystem, it continues to evolve at a higher level of intelligence.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.169,"cache_write":2.1125,"input":1.69,"output":5.07},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-2.4t-a95b","name":"qwen3.8-2.4t-a95b","display_name":"qwen3.8-2.4t-a95b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":2,"output":6,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen3.8-2.4T-A95B is Alibaba’s most powerful Qwen model to date. It is a 2.4‑trillion‑parameter sparse Mixture-of-Experts (MoE) model with approximately 95 billion active parameters. It is built for autonomous, long‑duration tasks: multi‑day code runs, reproducing research papers, and self‑improvement.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.5,"input":2,"output":6},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.5","name":"grok-4.5","display_name":"grok-4.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.5},"limit":{"context":500000,"output":500000},"metadata":{"description":"Grok 4.5 was trained on datasets spanning knowledge in coding, science, engineering, and math. With both intelligent and efficient reasoning, Grok 4.5 excels at real engineering tasks and exceeds comparable leading models at these tasks.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.5,"input":2,"output":6,"tiers":[{"cache_read":1.1,"input":4.4,"output":13.2,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"lfm-2.5-2.6b-free","name":"lfm-2.5-2.6b-free","display_name":"lfm-2.5-2.6b-free","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":131072,"output":131072},"metadata":{"description":"LFM-2.5-2.6B is a compact reasoning model developed by Liquid, featuring a generous 128,000 token context length. It is highly suited for agent workflows, data extraction, retrieval-augmented generation (RAG), and long-context processing. However, the developer advises against using this model for agentic coding tasks.","typeHints":["llm"],"features":["reasoning","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-h3","name":"minimax-h3","display_name":"minimax-h3","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"description":"MiniMax H3 (minimax-h3) is a general-purpose omni-modal generation model developed by the Chinese AI company MiniMax. It can jointly understand text, images, video, and audio while generating videos of up to 15 seconds in 2K resolution with native stereo sound. It is designed for advertising, branding, e-commerce, product design, UI/UX, and gaming. Compared with Hailuo 01 and Hailuo 02, H3 evolves from specialized video generation into a unified model for multimodal creation, reference-based editing, text rendering, and motion transfer.","typeHints":["video"],"inputModalities":["text","image","video","audio"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":true},{"id":"agnes-2.5-flash","name":"agnes-2.5-flash","display_name":"agnes-2.5-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.03,"output":0.15},"limit":{"context":512000,"output":512000},"metadata":{"description":"Agnes 2.5 Flash is Agnes AI’s fast and efficient language model, an upgraded, fully available model based on Agnes 2.0 Flash. It continues to use an OpenAI-compatible Chat Completions interface and has been optimized for coding tasks, agent workflows, tool calls, multi-turn dialogue, reasoning, and image understanding.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"input":0.03,"output":0.15},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"agnes-2.5-pro","name":"agnes-2.5-pro","display_name":"agnes-2.5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.45,"output":0.9,"cache_read":0.00378},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Agnes 2.5 Pro is Agnes AI’s paid inference model and the commercially stable version of the Agnes 2.5 Pro Alpha ranking model, suitable for advanced coding, scientific reasoning, long-context analysis, agent workflows, and multimodal understanding. The model is accessed via an OpenAI-compatible Chat Completions API.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.00378,"input":0.45,"output":0.9},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"agnes-2.5-pro-alpha","name":"agnes-2.5-pro-alpha","display_name":"agnes-2.5-pro-alpha","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.45,"output":0.9,"cache_read":0.00378},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Agnes 2.5 Pro Alpha is Agnes AI’s paid inference model, suitable for advanced coding, scientific reasoning, long-context analysis, agent workflows, and multimodal understanding. The model is accessed via an OpenAI-compatible Chat Completions API.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.00378,"input":0.45,"output":0.9},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"agnes-image-2.1-flash","name":"agnes-image-2.1-flash","display_name":"agnes-image-2.1-flash","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Agnes Image 2.1 Flash is Agnes AI’s high-performance image generation and image editing model, supporting text-to-image, image-to-image, and multi-image composition. It is suitable for creative design, marketing visuals, e-commerce product images, and social content production.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":true},{"id":"claude-opus-5","name":"claude-opus-5","display_name":"claude-opus-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","typeHints":["llm"],"features":["thinking","tools","structured_outputs","long_context","web"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen-image-3.0","name":"qwen-image-3.0","display_name":"qwen-image-3.0","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen Image 3.0(qwen-image-3.0) is an image generation and editing model developed by Alibaba Cloud’s Qwen team. It supports text-to-image generation, reference-based creation, and image editing. It is well suited for social media, e-commerce, creative design, and everyday content production, offering a strong balance of image quality and speed. Compared with the Pro version, it is better suited for frequent and large-scale daily creation.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":2,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"qwen-image-3.0-pro","name":"qwen-image-3.0-pro","display_name":"qwen-image-3.0-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen Image 3.0 Pro (qwen-image-3.0-pro) is Alibaba Cloud Qwen’s flagship image generation and editing model. It is designed for advertising, brand visuals, UI, presentations, product imagery, and professional design. Its strengths include complex layouts, accurate Chinese and English text rendering, realistic materials, and reference-based editing. Compared with the standard version, it delivers stronger detail, composition, and commercial-grade visual quality.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":2,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.6-flash","name":"gemini-3.6-flash","display_name":"gemini-3.6-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at code generation, agentic execution, and spatial reasoning. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"ling-3.0-tiny-free","name":"ling-3.0-tiny-free","display_name":"ling-3.0-tiny-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, featuring 1.3B active parameters out of a total of 7.9B. It is designed for responsive agents, instruction following, and multi-turn conversations, supporting an extensive context length of 262,144 tokens. This makes it an efficient and powerful choice for conversational AI applications.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3.5-lightning-free","name":"nemotron-3.5-lightning-free","display_name":"nemotron-3.5-lightning-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring 3 billion active parameters out of 30 billion total. It supports an extensive context window of up to 1,000,000 tokens. This model is designed to deliver efficient performance for high-throughput agentic workloads and specialized tasks.\nCompared with Nemotron 3 Super and Ultra, Lightning is smaller and optimized for fast, high-volume execution, while the larger models focus on complex planning and advanced reasoning.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k3","name":"kimi-k3","display_name":"kimi-k3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":2.84,"output":14.2,"cache_read":0.284},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.284,"input":2.84,"output":14.2},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ling-3.0-flash-free","name":"ling-3.0-flash-free","display_name":"ling-3.0-flash-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"Developed by Inclusionai, ling-3.0-flash-free is a 124B-parameter Mixture-of-Experts (MoE) model with approximately 5.1B parameters activated per token. Featuring an expansive context length of 262,144 tokens, this model is built to handle extensive datasets and long-form content. It is designed with token efficiency and production-scale agentic inference as key priorities to enable seamless developer deployment.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.2","name":"muse-spark-1.2","display_name":"muse-spark-1.2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":1.375,"output":4.675},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.","typeHints":["llm"],"features":["thinking","tools"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"input":1.375,"output":4.675},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.8-max-preview","name":"qwen3.8-max-preview","display_name":"qwen3.8-max-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.338,"output":1.014,"cache_read":0.0676},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen 3.8 Max Preview(Qwen3.8-Max-Preview)  is the latest-generation foundation model in the Qwen family, packing 2.4T parameters and still evolving. Compared with the previous flagship Qwen 3.7 Max, it delivers major gains in core capabilities like Coding and Cowork (professional productivity), with world-leading performance on complex, long-horizon tasks such as full-stack development, data analysis, and Office workflows.\nLaunch offer: Credits are consumed at just 20% of the standard rate, effectively 5× your usage. Limited time only.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":1.014},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-sonnet-5","name":"claude-sonnet-5","display_name":"claude-sonnet-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2,"output":10,"cache_read":0.2},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Sonnet 5 is the next generation of Anthropic's Sonnet model family. It is a drop-in upgrade for Claude Sonnet 4.6 with three behavior changes: adaptive thinking is on by default, manual extended thinking now returns a 400 error (it was deprecated on Claude Sonnet 4.6), and setting sampling parameters (temperature, top_p, top_k) to non-default values returns a 400 error","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"muse-spark-1.1","name":"muse-spark-1.1","display_name":"muse-spark-1.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":1.375,"output":4.675},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.","typeHints":["llm"],"features":["thinking","tools"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"input":1.375,"output":4.675},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen-audio-3.0-tts-flash","name":"qwen-audio-3.0-tts-flash","display_name":"qwen-audio-3.0-tts-flash","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"qwen-audio-3.0-tts-flash is a high-performance speech synthesis large model optimized for real-time interactive scenarios. Compared with the previous version, the model supports more low-resource languages and Chinese dialects, improves the authenticity of dialect pronunciation, and enhances free-style instruction following and fine-grained label control, enabling more flexible control of expression such as emotion, tone, character, speaking rate, and volume. At the same time, the model exhibits stronger robustness under complex acoustic conditions like noise and reverberation, improving sound quality, clarity, and overall expressiveness. The Flash version focuses on optimizing the real-time synthesis experience, keeping first-packet latency under 200 ms, making it suitable for low-latency interactive scenarios such as voice assistants, real-time dialogue, and intelligent customer service.","typeHints":["tts"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"qwen-audio-3.0-tts-plus","name":"qwen-audio-3.0-tts-plus","display_name":"qwen-audio-3.0-tts-plus","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"qwen-audio-3.0-tts-plus is a high-performance speech synthesis large model designed for high-quality speech generation scenarios. Compared with the previous version, the model supports more low-resource languages and Chinese dialects, significantly improving the authenticity of dialect pronunciation, and enhancing free-style instruction following and fine-grained label control capabilities, allowing more accurate control of emotion, tone, character, speaking rate, volume, and synthesis style. Meanwhile, the model exhibits stronger robustness under complex acoustic conditions such as noise and reverberation, further improving sound quality, clarity, resolution, and overall expressiveness. The Plus version places greater emphasis on synthesis quality and detail, making it suitable for professional scenarios that require higher sound quality, naturalness, and expressiveness, such as content creation, audiobooks, film and TV dubbing, brand voice design, and high-quality voice services.","typeHints":["tts"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"gemini-3.1-flash-lite-image","name":"gemini-3.1-flash-lite-image","display_name":"gemini-3.1-flash-lite-image","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"limit":{"context":65536,"output":65536},"metadata":{"description":"Google's newest, most compact, and most cost-effective image generation and editing model, designed for large-scale use.","typeHints":["image_generation","llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.025,"input":0.25,"output":1.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.5-flash-lite","name":"gemini-3.5-flash-lite","display_name":"gemini-3.5-flash-lite","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.3,"output":2.499999,"cache_read":0.03},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for high-throughput, low-cost execution for subagent tasks and document parsing. The model supports text, image, video, audio, and PDF inputs, and is designed for high-volume agentic workflows, simple data extraction, and applications where latency and API cost are the primary constraints.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499999},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5.2-fast-preview","name":"glm-5.2-fast-preview","display_name":"glm-5.2-fast-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":2.254,"output":7.889,"cache_read":0.5635},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"GLM-5.2-Fast-Preview is the high-speed version of Zhipu AI’s flagship model GLM-5.2, supporting a 1M ultra-long context. The model’s capabilities are aligned with the GLM-5.2 standard version, offering logical reasoning, long-text understanding, and code generation. Through inference acceleration optimizations, output TPS can reach 1.5–2× that of the GLM-5.2 standard version, significantly improving output speed. It is suitable for scenarios sensitive to output speed, such as real-time dialogue, multi-turn Agent calls, and streaming code generation.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.5635,"input":2.254,"output":7.889},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-fable-5","name":"claude-fable-5","display_name":"claude-fable-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":11,"output":55,"cache_read":1.1},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Anthropic's most capable widely released model, for the most demanding reasoning and long-horizon agentic work（This model is extremely expensive and is not recommended for casual use.）","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":1.1,"cache_write":13.75,"input":11,"output":55},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"jina-reranker-v3.5","name":"jina-reranker-v3.5","display_name":"jina-reranker-v3.5","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":131072,"output":131072},"metadata":{"description":"jina-reranker-v3.5 is a 0.6B-parameter multilingual listwise document reranker and a drop-in upgrade to jina-reranker-v3. It keeps the same last-but-not-late (LBNL) listwise interface — ranking a query against many candidates in one forward pass — while improving domain robustness, structured-data ranking, multilingual retrieval, and inference efficiency.","typeHints":["rerank"],"inputModalities":["text"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"hy3","name":"hy3","display_name":"hy3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1562,"output":0.6248,"cache_read":0.03905},"limit":{"context":256000,"output":256000},"metadata":{"description":"The Hy3 official version is honed for real-world business scenarios, using a Mixture-of-Experts (MoE) architecture with 295B total parameters and 21B activated parameters. It natively supports a 256K context window and offers multiple thinking modes: no_think (ultra-fast response), think_low (quick thinking), and think_high (deep reasoning), balancing ultra-fast responses, complex reasoning, and invocation cost. Compared with the Preview version, Hy3—based on real business feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and others—focuses on improving the Coding Agent, long-form understanding, multi-turn context continuity, search QA, and complex task execution, performing more stably in reducing hallucinations, improving task completion, and engineering usability. It is better suited to practical scenarios such as frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step Agent workflows.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.03905,"input":0.1562,"output":0.6248},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-8","name":"claude-opus-4-8","display_name":"claude-opus-4-8","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Opus 4.8 is Anthropic’s newest and most powerful publicly available model. It is suitable for the most complex tasks. It is Anthropic’s strongest model for complex reasoning, long-horizon agent programming, and highly autonomous work.claude-opus-4-8 does not display thought content by default; you need to set the additional parameter \"display\": \"summarized\" to enable it","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"doubao-seed-2-1-pro","name":"doubao-seed-2-1-pro","display_name":"doubao-seed-2-1-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.9295,"output":4.6475,"cache_read":0.1859},"limit":{"context":256000,"output":256000},"metadata":{"description":"A new generation of large models moving toward production-grade intelligence, comprehensively upgrading coding, agent, and multimodal capabilities with stronger autonomous planning, long-horizon execution, and dynamic recovery abilities to handle real, complex enterprise tasks.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.1859,"input":0.9295,"output":4.6475},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-2-1-turbo","name":"doubao-seed-2-1-turbo","display_name":"doubao-seed-2-1-turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.46475,"output":2.32375,"cache_read":0.09295},"limit":{"context":256000,"output":256000},"metadata":{"description":"Balancing performance and cost, comprehensively upgrading coding, agent, and multimodal capabilities, with stronger autonomous planning, long-horizon execution, and dynamic recovery abilities to handle real, complex enterprise tasks.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.09295,"input":0.46475,"output":2.32375},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mai-image-2.5-pro","name":"mai-image-2.5-pro","display_name":"mai-image-2.5-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"description":"MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With top-tier realism, precise text rendering, and powerful image editing capabilities, it debuted among the top three in AI image generation rankings. It is primarily targeted at commercial design, product photography, and professional creative work.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":5,"output":5},"source":"public-provider-conf"},"vision":true},{"id":"grok-build-0.1","name":"grok-build-0.1","display_name":"grok-build-0.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1,"output":2,"cache_read":0.2},"limit":{"context":256000,"output":256000},"metadata":{"description":"Fast coding model trained specifically for agentic coding workflows.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":1,"output":2},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mai-image-2.5","name":"mai-image-2.5","display_name":"mai-image-2.5","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"description":"MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With top-tier realism, precise text rendering, and powerful image editing capabilities, it debuted among the top three in AI image generation rankings. It is primarily targeted at commercial design, product photography, and professional creative work.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":5,"output":5},"source":"public-provider-conf"},"vision":true},{"id":"mai-image-2.5-flash","name":"mai-image-2.5-flash","display_name":"mai-image-2.5-flash","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.75,"output":1.75},"limit":{"context":8192,"output":8192},"metadata":{"description":"MAI-Image-2.5 is Microsoft's flagship AI image generation and editing model. With top-tier realism, precise text rendering, and powerful image editing capabilities, it debuted among the top three in AI image generation rankings. It is primarily targeted at commercial design, product photography, and professional creative work.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":1.75,"output":1.75},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.5-flash","name":"gemini-3.5-flash","display_name":"gemini-3.5-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"(This model has been officially taken offline; requests to gemini-3.5-flash will now be automatically routed to gemini-3.6-flash.)Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","deepsearch","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.075,"input":0.75,"output":3.75},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"coding-kimi-k3","name":"coding-kimi-k3","display_name":"coding-kimi-k3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.44,"output":1.61333,"cache_read":0.066},"limit":{"context":1048576,"output":1048576},"metadata":{"typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.066,"input":0.44,"output":1.61333},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"happyhorse-1.1-i2v","name":"happyhorse-1.1-i2v","display_name":"happyhorse-1.1-i2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"HappyHorse-1.1-I2V supports image-to-video generation, further enhancing visual texture, dynamic performance, and cross-segment consistency. The model can more accurately understand input images and carry forward the creative intent, delivering significant improvements in character skin texture, ID consistency across segments, motion smoothness, text rendering stability, and audio–visual synchronization, producing higher-quality videos that are more realistic and natural, rich in detail, and more consistent.","typeHints":["video"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"happyhorse-1.1-r2v","name":"happyhorse-1.1-r2v","display_name":"happyhorse-1.1-r2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"HappyHorse-1.1-R2V supports reference-based video generation, further improving the stable preservation of subject, scene style, and visual consistency. The model supports up to nine reference images as input, and can more accurately understand and carry forward creative intent, offering stronger controllability and expressiveness in characters, scenes, style, and camera/shot performance.","typeHints":["video"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"happyhorse-1.1-t2v","name":"happyhorse-1.1-t2v","display_name":"happyhorse-1.1-t2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"HappyHorse-1.1-T2V supports text-to-video generation, further enhancing text semantic understanding, camera/shot orchestration, and dynamic generation performance. The model can more accurately realize creative intent, producing higher-quality videos with smoother, more natural movements, richer detail, and greater consistency in character actions, scene atmosphere, visual aesthetics, and physical motion.","typeHints":["video"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"coding-glm-5.2-free","name":"coding-glm-5.2-free","display_name":"coding-glm-5.2-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"coding glm 5.2 free (coding-glm-5.2-free)  is a free coding-focused API route offered by AIHubMix, powered by Z.ai’s open-source flagship GLM-5.2 model. It is suitable for code generation, debugging, project-level development, tool use, and long-running agent tasks, with support for reasoning, function calling, and structured outputs. Compared with GLM-5.1, it offers stronger coding capabilities and a 1-million-token context window. Each account is limited to 5 requests per minute, 100 requests per day, and 1 million free tokens per day.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-kimi-k3-free","name":"coding-kimi-k3-free","display_name":"coding-kimi-k3-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"coding-kimi-k3-free is the open and free version of coding-kimi-k3. To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-image","name":"gemini-3.1-flash-image","display_name":"gemini-3.1-flash-image","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image","pdf","video"]},"cost":{"input":0.5,"output":3,"cache_read":0.05},"limit":{"context":131072,"output":131072},"metadata":{"description":"gemini-3.1-flash-image (Nano Banana 2) features professional-grade visual intelligence, lightning-fast efficiency, and realistic, grounded generative capabilities. This model serves as the high-efficiency counterpart to Gemini 3 Pro Image, optimized for speed and high-volume developer use cases.","typeHints":["image_generation","llm"],"features":["thinking"],"inputModalities":["text","image","pdf","video"],"pricing":{"cache_read":0.05,"input":0.5,"output":3},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.7-code","name":"kimi-k2.7-code","display_name":"kimi-k2.7-code","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.95,"output":3.9995,"cache_read":0.160835},"limit":{"context":262144,"output":262144},"metadata":{"description":"Kimi K2.7 Code is Kimi’s most intelligent Coding model, capable of completing programming tasks with higher success rates in long context. It features a native multimodal architecture that supports text, image, video input, and thinking modes, and dialogue and agent tasks.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.160835,"input":0.95,"output":3.9995},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.7-code-highspeed","name":"kimi-k2.7-code-highspeed","display_name":"kimi-k2.7-code-highspeed","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":1.9,"output":7.999,"cache_read":0.32167},"limit":{"context":262144,"output":262144},"metadata":{"description":"High-Speed version of Kimi K2.7 Code model, with output speed of approximately 180 Tokens/s and up to 260 Tokens/s in short context scenarios, delivering a more extreme coding experience.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.32167,"input":1.9,"output":7.999},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-audio-1.5","name":"gpt-audio-1.5","display_name":"gpt-audio-1.5","type":"audio","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","audio"]},"cost":{"input":2.5,"output":10},"limit":{"context":128000,"output":128000},"metadata":{"description":"The gpt-audio model is OpenAI's first officially released (generally available) audio model. It supports audio input and output and can be used in Chat Completions.","typeHints":["tts","stt"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","audio"],"pricing":{"input":2.5,"output":10},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"hy-3d-3.1","name":"hy-3d-3.1","display_name":"hy-3d-3.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Using the Hunyuan Sheng 3D 3.1 model, it can generate higher-precision and higher-quality 3D models, supporting text-to-3D, image-to-3D, eight-view-to-3D, single-geometry generation (untextured model), sketch-to-3D, and intelligent topology-to-3D features.","typeHints":["3d"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"kling-v3-omni","name":"kling-v3-omni","display_name":"kling-v3-omni","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"VIDEO 3.0 Omni: All-in-One Multimodal Input, Voice-Driven Characters, Direct Audio-Visual Output, and Storyboarding Building on the Kling VIDEO O1 and Kling VIDEO 2.6, the Kling 3.0 Model Series leverage a deeply integrated unified model training framework, achieving more native multimodal input and output. It combines Native Audio with Element Consistency Control, and breaks through duration limits.","typeHints":["video"],"inputModalities":["text","image","video"],"source":"public-provider-conf"},"vision":true},{"id":"kling-video-o1","name":"kling-video-o1","display_name":"kling-video-o1","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Kling Video O1 is a major unified multimodal video model launched by Kuaishou. It integrates text, images, video, and subject inputs into a single engine, focusing on addressing the \"consistency\" pain point in AI video, and is very suitable for professional teams in e-commerce, advertising, and continuity-driven creation that need to maintain the appearance of characters and objects unchanged across scenes.","typeHints":["video"],"inputModalities":["text","image","video"],"source":"public-provider-conf"},"vision":true},{"id":"longcat-2.0","name":"longcat-2.0","display_name":"longcat-2.0","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.7746,"output":3.0984,"cache_read":0.015492},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Designed for agent development scenarios, it natively supports tool invocation, multi-step reasoning, and long-context tasks; it excels at code generation, automated workflows, and executing complex instructions; and it is deeply adapted to productivity tools such as Claude Code, OpenClaw, OpenCode, and Kilo Code.","typeHints":["llm"],"features":["thinking","tools"],"inputModalities":["text"],"pricing":{"cache_read":0.015492,"input":0.7746,"output":3.0984},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-nano-9b-v2-free","name":"nemotron-nano-9b-v2-free","display_name":"nemotron-nano-9b-v2-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":131072,"output":131072},"metadata":{"description":"NVIDIA-Nemotron-Nano-9B-v2-free is a large language model trained from scratch by NVIDIA. Designed as a unified model, it efficiently handles both reasoning and non-reasoning tasks to respond to a wide range of user queries. With a generous context length of 128,000 tokens, it is highly capable of processing long and complex documents.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-pro-image","name":"gemini-3-pro-image","display_name":"gemini-3-pro-image","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":12},"limit":{"context":65536,"output":65536},"metadata":{"description":"Gemini-3-Pro-Image (Nano Banana Pro) is a high-performance image generation and editing model built on Gemini 3 Pro. It delivers enhanced multimodal understanding and real-world semantic reasoning, enabling fast creation of well-structured visual content such as infographics, product sketches, and multi-subject scenes. It can also leverage real-time knowledge through Search grounding. The model excels in text rendering, consistent multi-image blending, and identity preservation, while offering fine-grained creative controls like localized edits, lighting and focus adjustments, camera transformations, and flexible aspect ratios. It’s ideal for rapid design, concept previews, product visualization, and everyday image generation workflows.","typeHints":["image_generation","llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"input":2,"output":12},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-4o-transcribe-diarize","name":"gpt-4o-transcribe-diarize","display_name":"gpt-4o-transcribe-diarize","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","audio"]},"cost":{"input":2.5,"output":10},"limit":{"context":16000,"output":16000},"metadata":{"description":"GPT-4o Transcribe Diarize is an automatic speech recognition (ASR) model with built-in speaker diarization, meaning it can associate audio segments in a conversation with different speakers.","typeHints":["stt"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","audio"],"pricing":{"input":2.5,"output":10},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.7-flash","name":"qwen3.7-flash","display_name":"qwen3.7-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.0282,"output":0.1128,"cache_read":0.00564},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The Qwen 3.7 series' mid-to-high cost-performance \"Plus\" model builds on strong text capabilities with a comprehensive upgrade to vision-language abilities, while retaining full agent capabilities in coding, tool use, and productivity workflows. Its core features are multimodal interactive hybrid agent capabilities, able to perceive real-world scenes, read screens and operate GUIs, generate code based on visual references, and provide end-to-end navigation of mobile applications.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.00564,"cache_write":0.03525,"input":0.0282,"output":0.1128,"tiers":[{"cache_read":0.0169,"cache_write":0.105625,"input":0.0845,"output":0.338,"tier":{"size":32000,"type":"context"}},{"cache_read":0.0338,"cache_write":0.21125,"input":0.169,"output":0.676,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.7-plus","name":"qwen3.7-plus","display_name":"qwen3.7-plus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.282,"output":1.128,"cache_read":0.0564},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The Qwen 3.7 series' mid-to-high cost-performance \"Plus\" model builds on strong text capabilities with a comprehensive upgrade to vision-language abilities, while retaining full agent capabilities in coding, tool use, and productivity workflows. Its core features are multimodal interactive hybrid agent capabilities, able to perceive real-world scenes, read screens and operate GUIs, generate code based on visual references, and provide end-to-end navigation of mobile applications.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.0564,"cache_write":0.3525,"input":0.282,"output":1.128,"tiers":[{"cache_read":0.169,"cache_write":1.05625,"input":0.845,"output":3.38,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"step-3.7-flash","name":"step-3.7-flash","display_name":"step-3.7-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.22,"output":1.32,"cache_read":0.044},"limit":{"context":256000,"output":256000},"metadata":{"description":"step-3.7-flash is stepfun's flagship inference model, designed for high-complexity tasks that require deep reasoning and fast execution. It excels at decomposing multi-step problems, performing tool calls, and maintaining consistency across massive datasets. It is the preferred choice for complex workloads such as long-context agents, advanced software engineering, and end-to-end research automation.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.044,"input":0.22,"output":1.32},"source":"public-provider-conf"},"vision":true},{"id":"minimax-m3","name":"minimax-m3","display_name":"minimax-m3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.288,"output":1.152},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The MiniMax M3 is a flagship programming model built for real-world productivity. As a production-grade model natively designed for Agent scenarios, it has achieved state-of-the-art (SOTA) performance in coding, agentic tool use, search, and office work.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.288,"output":1.152},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-nano-12b-v2-vl-free","name":"nemotron-nano-12b-v2-vl-free","display_name":"nemotron-nano-12b-v2-vl-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0,"output":0},"limit":{"context":131072,"output":131072},"metadata":{"description":"Developed by Nvidia, Nemotron-Nano-12B-V2-VL-Free is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It features a powerful 128,000-token context length to handle extensive visual and textual inputs. The model utilizes a hybrid Transformer-Mamba architecture, successfully combining transformer-level accuracy with Mamba's structural advantages.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text","image","video"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3-super-120b-a12b-free","name":"nemotron-3-super-120b-a12b-free","display_name":"nemotron-3-super-120b-a12b-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model built on a hybrid Mamba-Transformer architecture. Activating just 12B parameters, it delivers maximum compute efficiency and accuracy for complex multi-agent applications. Additionally, it features an expansive context length of 262,144 tokens to handle large-scale inputs seamlessly.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-8-think","name":"claude-opus-4-8-think","display_name":"claude-opus-4-8-think","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The claude-opus-4-8-think model has adaptive thinking mode pre-enabled; the default thinking intensity is \"medium\", and it can be invoked directly via the OpenAI unified API. The claude-opus-4-8 model does not display thinking content by default; you need to set the extra parameter \"display\": \"summarized\" to enable it.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"nemotron-3-nano-omni-30b-a3b-reasoning-free","name":"nemotron-3-nano-omni-30b-a3b-reasoning-free","display_name":"nemotron-3-nano-omni-30b-a3b-reasoning-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"Developed by Nvidia, NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. Supporting a massive context length of 256,000 tokens, it accepts and processes inputs across text, images, and video. This model provides powerful multimodal comprehension tailored for complex enterprise workflows.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text","image","video","audio"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3-ultra-550b-a55b-free","name":"nemotron-3-ultra-550b-a55b-free","display_name":"nemotron-3-ultra-550b-a55b-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model featuring an extensive 1,000,000-token context length. Built on a hybrid Transformer-Mamba mixture-of-experts (MoE) architecture, it operates with 55B active parameters out of a total of 550B parameters. This advanced structure is designed to support sophisticated reasoning and complex task orchestration.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.7-max","name":"qwen3.7-max","display_name":"qwen3.7-max","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.69,"output":5.07,"cache_read":0.169},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The Max model, the largest and most capable in the Qwen3.7 series, is currently offering its pure-text model capabilities for trial. Qwen3.7 is a new-generation flagship model designed for the agent era; its core strengths lie in the breadth and depth of its agent capabilities: it performs excellently in programming, office and productivity tasks, and long-term autonomous execution.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.169,"cache_write":2.1125,"input":1.69,"output":5.07},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-image-2","name":"gpt-image-2","display_name":"gpt-image-2","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":30,"cache_read":1.25},"limit":{"context":8192,"output":8192},"metadata":{"description":"GPT-image-2 is OpenAI's latest cutting-edge image generation model. Key value adds include better performance, quality, editing controls, and face preservation.\n(Currently the model's image generation time may be >5 minutes; it is recommended to set the client timeout to ≥10 minutes.)\nThe model supports high input_fidelity and adding/removing one aspect of the image while retaining others. This model includes improvements in aspect ratio, resolution, and editing capabilities.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"cache_read":1.25,"input":5,"output":30},"source":"public-provider-conf"},"vision":true},{"id":"nemotron-3.5-content-safety-free","name":"nemotron-3.5-content-safety-free","display_name":"nemotron-3.5-content-safety-free","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0,"output":0},"limit":{"context":131072,"output":131072},"metadata":{"description":"Developed by NVIDIA, Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. Supporting an expansive context length of 128,000 tokens, this model moderates both user inputs and generated responses for LLMs and VLMs. It provides robust safety filtering to ensure aligned and secure interactions across multiple modalities.","typeHints":["llm"],"features":["reasoning","long_context"],"inputModalities":["text","image"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.3","name":"grok-4.3","display_name":"grok-4.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok 4.3 is amongst the leading models in intelligence and well priced when comparing to other models of similar price. It's also notably fast, however very verbose. The model supports text and image input, outputs text, and has a 1m tokens context window.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":1.25,"output":2.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"happyhorse-1.0-i2v","name":"happyhorse-1.0-i2v","display_name":"happyhorse-1.0-i2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"HappyHorse-1.0-I2V supports image-to-video generation, featuring highly faithful dynamic visual generation capabilities, accurately understanding textual semantics and producing smooth, natural, and detail-rich high-quality videos.","typeHints":["video"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"happyhorse-1.0-r2v","name":"happyhorse-1.0-r2v","display_name":"happyhorse-1.0-r2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"HappyHorse-1.0-R2V supports reference-guided video generation, offering more stable subject and scene referencing, supports up to 9 reference images, and can accurately maintain creative intent to achieve stronger expressive capabilities.","typeHints":["video"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"happyhorse-1.0-t2v","name":"happyhorse-1.0-t2v","display_name":"happyhorse-1.0-t2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"HappyHorse-1.0-T2V supports text-to-video generation, featuring highly faithful dynamic visual generation capabilities, accurately understanding textual semantics and producing smooth, natural, and detail-rich high-quality videos.","typeHints":["video"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"happyhorse-1.0-video-edit","name":"happyhorse-1.0-video-edit","display_name":"happyhorse-1.0-video-edit","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","video","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"HappyHorse-1.0-Video-Edit supports video editing, allows editing videos via natural language commands, can reference up to 5 images to edit video elements locally or globally, and can accurately replicate video dynamics to achieve stronger expressive capabilities.","typeHints":["video"],"inputModalities":["text","video","image"],"source":"public-provider-conf"},"vision":true},{"id":"north-mini-code-free","name":"north-mini-code-free","display_name":"north-mini-code-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":256000,"output":256000},"metadata":{"description":"Developed by Cohere, north-mini-code-free is the debut model of the North family and Cohere's first agentic coding model. This sparse mixture-of-experts model features 30B total parameters and 3B active parameters, designed and optimized for high performance. With an expansive context length of 256,000 tokens, it is well-suited for handling complex developer workflows and large codebases.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5.2","name":"coding-glm-5.2","display_name":"coding-glm-5.2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Currently, the special resources for this model are limited, but due to its popularity, the usage is too high, which may result in a large number of 429 errors. Resources have been coordinated, and improvements are expected in the coming weeks, so please stay tuned. In the meantime, it is recommended to use the regular-priced API model, which can ensure absolute stability. The model ID is glm-5.2.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ernie-5.1","name":"ernie-5.1","display_name":"ernie-5.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.5634,"output":2.5353,"cache_read":0.5634},"limit":{"context":119000,"output":119000},"metadata":{"description":"ERNIE 5.1 is the latest model in the Wenxin series, with comprehensive upgrades to its foundational capabilities and significant improvements in agents, knowledge, reasoning, and deep search. This upgrade uses a decoupled fully-asynchronous reinforcement learning technique to specifically address challenges encountered as large models evolve toward agent-based autonomous decision-making, such as training–inference numerical bias, low utilization of heterogeneous resources, and global issues caused by long-tail effects. It is paired with scaled agent post-training techniques to enhance model capabilities and generalization, enabling a three-step collaboration of environment, expert, and fusion that both ensures training efficiency and significantly improves the model’s stability and performance on complex tasks.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.5634,"input":0.5634,"output":2.5353,"tiers":[{"cache_read":0.845,"input":0.845,"output":3.098361,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-lite","name":"gemini-3.1-flash-lite","display_name":"gemini-3.1-flash-lite","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-3.1-flash-lite is currently Google's latest and most cost-effective model, optimized for large-scale agent-based tasks, translation, and simple data processing.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","deepsearch","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.025,"input":0.25,"output":1.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-lite-nothink","name":"gemini-3.1-flash-lite-nothink","display_name":"gemini-3.1-flash-lite-nothink","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-3.1-flash-lite is currently Google's latest and most cost-effective model, optimized for large-scale agent-based tasks, translation, and simple data processing.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","deepsearch","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.025,"input":0.25,"output":1.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.5","name":"gpt-5.5","display_name":"gpt-5.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":30,"cache_read":0.5},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-5.5 raises the baseline for complex production workflows. It’s a strong fit for coding use cases, tool-heavy agents, grounded assistants, long-context retrieval, product-spec-to-plan workflows, and customer-facing workflows where execution quality and response polish are critical.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs","web","tools"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"input":5,"output":30,"tiers":[{"cache_read":1,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.5-pro","name":"gpt-5.5-pro","display_name":"gpt-5.5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":30,"output":180},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"Please note: this model is extremely expensive and very slow. If a request fails due to network issues, you may still be charged heavily; we cannot refund charges incurred by requests to this model.\nGPT-5.5 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.5 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeout, please set a longer timeout duration. It is recommended to use this under good network conditions.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"laguna-xs-2.1-free","name":"laguna-xs-2.1-free","display_name":"laguna-xs-2.1-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside, representing a step forward from the Laguna XS.2 model released in April 2026. It features an extensive context length of 262,144 tokens, allowing it to process large amounts of code and developer inputs. This model provides a robust solution for a wide range of coding agent tasks.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-v4-flash","name":"deepseek-v4-flash","display_name":"deepseek-v4-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.142,"output":0.284,"cache_read":0.0284},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"(This model currently points to the older 0423 version; if you need to request the latest version, you can choose the model deepseek-v4-flash-0731)DeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.0284,"input":0.142,"output":0.284},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek-v4-pro","name":"deepseek-v4-pro","display_name":"deepseek-v4-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.69,"output":3.38,"cache_read":0.14027},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"(This model currently points to the older 0423 version; if you need to request the latest version, you can choose the model deepseek-v4-pro-0813)DeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.( Directly requesting deepseek-v4-pro will route you through the official discount channel.)","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.14027,"input":1.69,"output":3.38},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"doubao-seedream-5.0-pro","name":"doubao-seedream-5.0-pro","display_name":"doubao-seedream-5.0-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedream-5.0-pro is the latest image-creation model released by ByteDance. The model advances image creation to a new stage of controllable production. The main highlights of this update are more controllable editing, more production-ready generation, and more natural results.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":2,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"ernie-5.0","name":"ernie-5.0","display_name":"ernie-5.0","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.82192,"output":3.28768,"cache_read":0.82192},"limit":{"context":119000,"output":119000},"metadata":{"description":"ERNIE 5.0 is the next-generation natively multimodal foundation model in the ERNIE family. Built on a unified multimodal architecture, it jointly learns from text, images, audio, and video to deliver broad multimodal capabilities.\n\nERNIE 5.0 features significantly upgraded core capabilities and shows strong performance across benchmarks, with notable gains in multimodal understanding, instruction following, creative writing, factual accuracy, and agent planning with tool use.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.82192,"input":0.82192,"output":3.28768,"tiers":[{"cache_read":1.36986,"input":1.36986,"output":5.47944,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2.6","name":"kimi-k2.6","display_name":"kimi-k2.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.95,"output":3.9995,"cache_read":0.160835},"limit":{"context":262144,"output":262144},"metadata":{"description":"Kimi K2.6 is Kimi's latest and most intelligent model, with stronger and more stable long-range code-writing capabilities, significantly improved instruction-following and self-correction abilities, and support for text, image, and video inputs, thinking and non-thinking modes, as well as dialogue and Agent tasks.The model has a context length of 256k, supports long-form thinking, and excels at deep reasoning.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.160835,"input":0.95,"output":3.9995},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"laguna-s-2.1-free","name":"laguna-s-2.1-free","display_name":"laguna-s-2.1-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Laguna S 2.1 is the latest coding agent model from Poolside, featuring an impressive context length of 262,144 tokens. This model is built with 118B total parameters and 8B active parameters, balancing efficiency with high performance. It delivers strong capabilities for developer tasks, scoring 70.2% on the Terminal-Bench 2.1 benchmark.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2.5","name":"mimo-v2.5","display_name":"mimo-v2.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.155,"output":0.31,"cache_read":0.0031},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"MiMo-V2.5 is a native, fully multimodal large model designed for agent scenarios; it can see, hear, and read, and translate understanding into action. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M context length. Built on a powerful model base, we continuously scale compute across broader agent scenarios, further expanding the agent’s action space and achieving an important generalization from coding to claw.","typeHints":["llm"],"features":["web"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.0031,"input":0.155,"output":0.31},"source":"public-provider-conf"},"vision":true},{"id":"mimo-v2.5-pro","name":"mimo-v2.5-pro","display_name":"mimo-v2.5-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.48,"output":0.96,"cache_read":0.00384},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"MiMo-V2.5-Pro is Xiaomi's most powerful model to date. In areas such as general agent capabilities, complex software engineering, and long-horizon tasks, it can now directly compete with the world's top agent models (Claude Opus 4.6, GPT-5.4). Compared with the previous-generation MiMo-V2-Pro, it achieves an all-around leap forward.","typeHints":["llm"],"features":["web"],"inputModalities":["text"],"pricing":{"cache_read":0.00384,"input":0.48,"output":0.96},"source":"public-provider-conf"},"vision":false},{"id":"command-a-plus-05-2026","name":"command-a-plus-05-2026","display_name":"command-a-plus-05-2026","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2.5,"output":10},"limit":{"context":128000,"output":128000},"metadata":{"description":"Cohere's stronger command model for multilingual agents and enterprise workflows","typeHints":["llm"],"features":["thinking","tools","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":2.5,"output":10},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.6-max-preview","name":"qwen3.6-max-preview","display_name":"qwen3.6-max-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.268,"output":7.608,"cache_read":0.1268},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Max model Preview version, the largest and most capable model in the Qwen3.6 series, currently offers its pure-text model capabilities for trial. Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model further enhances vibe coding capabilities, executes coding agents more efficiently, significantly improves front-end programming and development capabilities, and further upgrades long-tail knowledge handling.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.1268,"cache_write":1.585,"input":1.268,"output":7.608,"tiers":[{"cache_read":0.2112,"cache_write":2.64,"input":2.112,"output":12.672,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.6-27b","name":"qwen3.6-27b","display_name":"qwen3.6-27b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.422,"output":2.532},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen3.6 series 27B native vision-language Dense model. Compared with the 3.5-27B, the model notably improves Agentic coding capability and further enhances STEM and reasoning abilities; on the visual modality side, spatial intelligence, object localization and detection capabilities are significantly strengthened, and video understanding, document OCR, and visual agent capabilities have steadily improved.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"input":0.422,"output":2.532},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.6-35b-a3b","name":"qwen3.6-35b-a3b","display_name":"qwen3.6-35b-a3b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.254,"output":1.524},"limit":{"context":262144,"output":262144},"metadata":{"description":"Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding performance comparable to the current top cutting-edge models, with a significant improvement over the 3.5 series. The model's capabilities have been markedly enhanced in Agentic coding, front-end programming, Vibe coding and other coding abilities, universal multimodal recognition, OCR, object localization, and more.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"input":0.254,"output":1.524},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.6-flash","name":"qwen3.6-flash","display_name":"qwen3.6-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.169,"output":1.014,"cache_read":0.0169},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding performance comparable to the current top cutting-edge models, with a significant improvement over the 3.5 series. The model's capabilities have been markedly enhanced in Agentic coding, front-end programming, Vibe coding and other coding abilities, universal multimodal recognition, OCR, object localization, and more.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.0169,"cache_write":0.21125,"input":0.169,"output":1.014,"tiers":[{"cache_read":0.0676,"cache_write":0.845,"input":0.676,"output":4.056,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-chat-latest","name":"gpt-chat-latest","display_name":"gpt-chat-latest","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":30,"cache_read":0.5},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates in the future, they are routed behind this slug automatically.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs","web","tools"],"inputModalities":["text","image"],"pricing":{"cache_read":0.5,"input":5,"output":30,"tiers":[{"cache_read":1,"input":10,"output":45,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"nemotron-3-nano-30b-a3b-free","name":"nemotron-3-nano-30b-a3b-free","display_name":"nemotron-3-nano-30b-a3b-free","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"NVIDIA Nemotron 3 Nano 30B A3B is a highly efficient small language Mixture of Experts (MoE) model developed by Nvidia. Designed to help developers build specialized agentic AI systems, it delivers exceptional compute efficiency and accuracy. Additionally, it features an impressive context length of 256,000 tokens to support extensive data processing.","typeHints":["llm"],"features":["reasoning","tool_calling","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7","name":"claude-opus-4-7","display_name":"claude-opus-4-7","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Opus 4.7 is Anthropic’s latest and most powerful publicly available model. It has high autonomy and performs exceptionally well on long-horizon agent tasks, knowledge work, vision tasks, and memory tasks.  The claude-opus-4-7 model does not display thinking content by default; you need to set the extra parameter \"display\": \"summarized\" to enable it.This page summarizes all the new features at release.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-opus-4-7-think","name":"claude-opus-4-7-think","display_name":"claude-opus-4-7-think","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The claude-opus-4-7-think model has adaptive thinking mode pre-enabled; the default thinking intensity is \"medium\", and it can be invoked directly via the OpenAI unified API. The claude-opus-4-7 model does not display thinking content by default; you need to set the extra parameter \"display\": \"summarized\" to enable it.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"cohere-rerank-v4.0-fast","name":"cohere-rerank-v4.0-fast","display_name":"cohere-rerank-v4.0-fast","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.068,"output":0},"limit":{"context":32768,"output":32768},"metadata":{"description":"Rerank 4 is the most advanced set of reranker models available today, purpose-built to meet the realities and challenges of enterprise AI search. It delivers best-in-class retrieval, outperforming the likes of MongoDB’s Voyage models and ElasticSearch’s Jina rerankers in overall search relevance, as well as improved latency, flexible deployment options, deep customizability and robust multilingual performance. Designed for business-critical applications across key industries and domains, Rerank 4 sets a new standard for accuracy and adaptability in enterprise search.","typeHints":["rerank"],"inputModalities":["text"],"pricing":{"input":0.068,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"cohere-rerank-v4.0-pro","name":"cohere-rerank-v4.0-pro","display_name":"cohere-rerank-v4.0-pro","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.068,"output":0},"limit":{"context":32768,"output":32768},"metadata":{"description":"Rerank 4 is the most advanced set of reranker models available today, purpose-built to meet the realities and challenges of enterprise AI search. It delivers best-in-class retrieval, outperforming the likes of MongoDB’s Voyage models and ElasticSearch’s Jina rerankers in overall search relevance, as well as improved latency, flexible deployment options, deep customizability and robust multilingual performance. Designed for business-critical applications across key industries and domains, Rerank 4 sets a new standard for accuracy and adaptability in enterprise search.","typeHints":["rerank"],"inputModalities":["text"],"pricing":{"input":0.068,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"qwen-image-2.0","name":"qwen-image-2.0","display_name":"qwen-image-2.0","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen-Image-2.0 series accelerated models integrate image generation and image editing; they offer more professional text rendering with support for 1k-token instructions, finer realistic textures and delicate portrayal of photorealistic scenes, and stronger semantic adherence. The accelerated version effectively achieves an optimal balance between model quality and performance.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"qwen-image-2.0-pro","name":"qwen-image-2.0-pro","display_name":"qwen-image-2.0-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen-Image-2.0 full-powered models achieve the integration of image generation and image editing; they offer more professional text rendering with support for 1k-token instructions, more refined photorealistic textures and delicate depiction of realistic scenes, and stronger semantic adherence. The full-powered version delivers the strongest text rendering capability and realism in the 2.0 series.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"grok-4-20-non-reasoning","name":"grok-4-20-non-reasoning","display_name":"grok-4-20-non-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal understanding, and enterprise use. It improves instruction following, honesty, and calibration over earlier Grok versions, while supporting both single‑agent and multi‑agent workflows. Designed as a general‑purpose, truth‑seeking assistant, Grok 4.2 is well suited for research, analysis, coding, and complex professional tasks when deployed with appropriate guardrails.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":2,"output":6},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4-20-reasoning","name":"grok-4-20-reasoning","display_name":"grok-4-20-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal understanding, and enterprise use. It improves instruction following, honesty, and calibration over earlier Grok versions, while supporting both single‑agent and multi‑agent workflows. Designed as a general‑purpose, truth‑seeking assistant, Grok 4.2 is well suited for research, analysis, coding, and complex professional tasks when deployed with appropriate guardrails.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":2,"output":6},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3.6-plus","name":"qwen3.6-plus","display_name":"qwen3.6-plus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.282,"output":1.692,"cache_read":0.0282},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen 3.6, the native vision-language Plus series model, demonstrates outstanding performance comparable to the current top cutting-edge models, with a significant improvement over the 3.5 series. The model's capabilities have been markedly enhanced in Agentic coding, front-end programming, Vibe coding and other coding abilities, universal multimodal recognition, OCR, object localization, and more.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.0282,"cache_write":0.3525,"input":0.282,"output":1.692,"tiers":[{"cache_read":0.1128,"cache_write":1.41,"input":1.128,"output":6.768,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"wan2.7-i2v","name":"wan2.7-i2v","display_name":"wan2.7-i2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wanxiang 2.7 — image-to-video: performance capabilities comprehensively upgraded. Dramatic/dialogue scenes convey delicate, natural emotions; action scenes are fierce, with every punch landing hard. Combined with more dramatic, rhythmically paced camera cuts, it achieves stronger overall performance.","typeHints":["video"],"inputModalities":["text","image","audio"],"source":"public-provider-conf"},"vision":true},{"id":"wan2.7-r2v","name":"wan2.7-r2v","display_name":"wan2.7-r2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wanxiang 2.7 — reference-driven video generation: more stable references for characters, props, and scenes; supports up to five mixed image/video references; supports audio/timbre references; combined with foundational capability upgrades to deliver stronger performance.","typeHints":["video"],"inputModalities":["text","image","video","audio"],"source":"public-provider-conf"},"vision":true},{"id":"wan2.7-t2v","name":"wan2.7-t2v","display_name":"wan2.7-t2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wanxiang 2.7 — text-to-video: performance capabilities comprehensively upgraded. Dramatic/dialogue scenes convey delicate, natural emotions; action scenes are intense, with every punch landing hard. Paired with more dramatic and rhythmically paced camera cuts, it achieves stronger overall acting performance.","typeHints":["video"],"inputModalities":["text","audio"],"source":"public-provider-conf"},"vision":false},{"id":"wan2.7-videoedit","name":"wan2.7-videoedit","display_name":"wan2.7-videoedit","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wanxiang 2.7 — video editing: edit videos using natural-language commands, supporting local or global edits; can use reference images to replace video elements; supports replicating video actions, special effects, camera movements, and other dynamic processes.","typeHints":["video"],"inputModalities":["text","image","video"],"source":"public-provider-conf"},"vision":true},{"id":"coding-minimax-m3-free","name":"coding-minimax-m3-free","display_name":"coding-minimax-m3-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0,"output":0},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"coding-minimax-m3-free is a free and open version offered by AIHubMix specifically for MiniMax users.  To maintain reliable service, each account is limited to 5 requests per minute, 500 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seedance-2-0-260128","name":"doubao-seedance-2-0-260128","display_name":"doubao-seedance-2-0-260128","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Doubao large-model team has launched a new-generation professional-grade multimodal video-creation model, Seedance 2.0. It supports images, videos, and audio as multimodal reference inputs to generate videos, and also offers video editing and extension capabilities. It can accurately reproduce various details while maintaining stable character features, delivers highly realistic audiovisual stability, and is deeply adapted to core scenarios such as commercial advertising, film and TV production, and social media marketing.","typeHints":["video"],"inputModalities":["text","image","video","audio"],"source":"public-provider-conf"},"vision":true},{"id":"doubao-seedance-2-0-fast-260128","name":"doubao-seedance-2-0-fast-260128","display_name":"doubao-seedance-2-0-fast-260128","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedance 2.0 fast is a next-generation multimodal video-creation model launched by the Doubao large-model team; it inherits the core features and advantages of Seedance 2.0 and generates content faster.","typeHints":["video"],"inputModalities":["text","image","video","audio"],"source":"public-provider-conf"},"vision":true},{"id":"doubao-seedance-2-0-mini-260615","name":"doubao-seedance-2-0-mini-260615","display_name":"doubao-seedance-2-0-mini-260615","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedance 2.0 mini is a next-generation, cost-effective video generation model launched to address broader video-generation needs. While maintaining competitive performance, it brings video-generation capabilities to lower barriers to entry, more frequent use, and more scalable/large-scale application scenarios.","typeHints":["video"],"inputModalities":["text","image","video","audio"],"source":"public-provider-conf"},"vision":true},{"id":"glm-5.1","name":"glm-5.1","display_name":"glm-5.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.845,"output":3.38,"cache_read":0.183112},"limit":{"context":200000,"output":200000},"metadata":{"description":"GLM-5.1 is Zhipu's latest flagship model, with greatly enhanced coding capabilities and significantly improved long-range task performance. It can continuously and autonomously work for up to 8 hours on a single task, completing the full closed loop from planning and execution to iterative optimization, delivering engineering-grade results.\nIn terms of general capability and coding ability, GLM-5.1's overall performance aligns with Claude Opus 4.6, and it demonstrates stronger sustained work capability in long-range autonomous execution, complex engineering optimization, and real-world development scenarios, making it an ideal foundation for building Autonomous Agents and long-horizon Coding Agents.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.183112,"input":0.845,"output":3.38},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-image","name":"glm-image","display_name":"glm-image","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-Image is Zhipu AI's new flagship image generation model. The model is trained entirely on domestic chips and adopts an original hybrid architecture combining \"autoregressive + diffusion decoder,\" balancing global instruction understanding with local detail depiction. It overcomes generation challenges in knowledge-intensive scenarios such as posters, PPTs, and popular science illustrations. This represents an important exploration towards the new generation of \"cognitive generation\" technology paradigms exemplified by Nano Banana Pro.","typeHints":["image_generation"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"gemma-4-26b-a4b-it","name":"gemma-4-26b-a4b-it","display_name":"gemma-4-26b-a4b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.14,"output":0.39998},"limit":{"context":262144,"output":262144},"metadata":{"description":"A Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"input":0.14,"output":0.39998},"source":"public-provider-conf"},"vision":true},{"id":"gemma-4-31b-it","name":"gemma-4-31b-it","display_name":"gemma-4-31b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.2,"output":0.4},"limit":{"context":262144,"output":262144},"metadata":{"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"input":0.2,"output":0.4},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.4","name":"gpt-5.4","display_name":"gpt-5.4","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2.5,"output":15,"cache_read":0.25},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-5.4 is our frontier model for complex professional work.Reasoning.effort supports: none (default), low, medium, high and xhigh.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs","web","tools"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.25,"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"wan2.7-image","name":"wan2.7-image","display_name":"wan2.7-image","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wanxiang 2.7 — image generation and editing: supports text-to-image, text-to-multi-image, image-to-multi-image, image editing, multi-image reference generation, and interactive editing, with stronger performance in text rendering, subject consistency, and following complex instructions.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"wan2.7-image-pro","name":"wan2.7-image-pro","display_name":"wan2.7-image-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wanxiang 2.7 — image generation and editing: supports text-to-image, text-to-multi-image, image-to-multi-image, image editing, multi-image reference generation, and interactive editing, with stronger performance in text rendering, subject consistency, and following complex instructions.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"cc-k2.6-code-preview","name":"cc-k2.6-code-preview","display_name":"cc-k2.6-code-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"limit":{"context":262144,"output":262144},"metadata":{"description":"for claude code","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.02,"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":true},{"id":"claude-sonnet-4-6","name":"claude-sonnet-4-6","display_name":"claude-sonnet-4-6","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":3,"output":15,"cache_read":0.3},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows. Use cases include: Agents: Sonnet 4.6 excels at complex, multi-step tasks requiring sustained reasoning and adaptive decision-making—ideal for workflows where reliability and autonomy matter most. Coding: Sonnet 4.6 is built for iterative development work, handling complex codebases without losing quality as you guide it through building, refactoring, and debugging. It can compress multi-day projects into hours with the technical depth to deliver production-ready solutions. Enterprise workflows: Sonnet 4.6 powers agents that manage professional projects from start to finish, leveraging memory to maintain context across files with a step-change improvement in creating spreadsheets, slides, and docs. Financial analysis: Sonnet 4.6 connects the dots across regulatory filings, market reports, and internal data—enabling sophisticated modeling and proactive compliance. Cybersecurity: Sonnet 4.6 brings professional-grade analysis to security workflows, correlating logs, vulnerability databases, and threat intelligence for proactive threat detection and automated incident response. Computer use: Sonnet 4.6 delivers confident, consistent navigation with more human-like browsing—enabling better web QA, workflow automation, and advanced user experiences.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"coding-xiaomi-mimo-v2.5","name":"coding-xiaomi-mimo-v2.5","display_name":"coding-xiaomi-mimo-v2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.08,"output":0.16,"cache_read":0.0016},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.0016,"input":0.08,"output":0.16},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-xiaomi-mimo-v2.5-pro","name":"coding-xiaomi-mimo-v2.5-pro","display_name":"coding-xiaomi-mimo-v2.5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.4,"cache_read":0.0016},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.0016,"input":0.2,"output":0.4},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-xiaomi-mimo-v2.6-pro","name":"coding-xiaomi-mimo-v2.6-pro","display_name":"coding-xiaomi-mimo-v2.6-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.4,"cache_read":0.0016},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.0016,"input":0.2,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"doubao-seed-2-0-lite-260428","name":"doubao-seed-2-0-lite-260428","display_name":"doubao-seed-2-0-lite-260428","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document","audio"]},"cost":{"input":0.09041,"output":0.54246,"cache_read":0.018082},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao  Coding model optimized for real-world programming environments that can reliably invoke tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports Skills and can work with various custom skills.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","document","audio"],"pricing":{"cache_read":0.018082,"input":0.09041,"output":0.54246,"tiers":[{"cache_read":0.027123,"input":0.135616,"output":0.813696,"tier":{"size":32000,"type":"context"}},{"cache_read":0.054246,"input":0.271232,"output":1.627392,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-2-0-mini-260428","name":"doubao-seed-2-0-mini-260428","display_name":"doubao-seed-2-0-mini-260428","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document","audio"]},"cost":{"input":0.030136,"output":0.30136,"cache_read":0.006027},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao  Coding model optimized for real-world programming environments that can reliably invoke tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports Skills and can work with various custom skills.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","document","audio"],"pricing":{"cache_read":0.006027,"input":0.030136,"output":0.30136,"tiers":[{"cache_read":0.012055,"input":0.060274,"output":0.60274,"tier":{"size":32000,"type":"context"}},{"cache_read":0.02411,"input":0.120548,"output":1.20548,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-image-preview","name":"gemini-3.1-flash-image-preview","display_name":"gemini-3.1-flash-image-preview","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.5,"output":3,"cache_read":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"gemini-3.1-flash-image-preview (Nano Banana 2) features professional-grade visual intelligence, lightning-fast efficiency, and realistic, grounded generative capabilities. This model serves as the high-efficiency counterpart to Gemini 3 Pro Image, optimized for speed and high-volume developer use cases.","typeHints":["image_generation","llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.05,"input":0.5,"output":3},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-pro-preview","name":"gemini-3.1-pro-preview","display_name":"gemini-3.1-pro-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":2,"output":12,"cache_read":0.2},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 3.1 Pro Preview is designed to further optimize the performance and reliability of the Gemini 3 Pro series, offering improved reasoning capabilities, greater token efficiency, and a more robust, factually consistent user experience. It is optimized for software-engineering behaviors and usability, and is also suitable for agent workflows that require precise tool invocation and reliable multi-step execution, enabling stable operation across a variety of real-world scenarios.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","deepsearch","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.2,"input":2,"output":12,"tiers":[{"cache_read":0.4,"input":4,"output":18,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.1-pro-preview-customtools","name":"gemini-3.1-pro-preview-customtools","display_name":"gemini-3.1-pro-preview-customtools","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":2,"output":12,"cache_read":0.2},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-3.1-pro-preview-customtools\n\nFor users who build applications mixing bash and custom tools, the Gemini 3.1 Pro preview provides a separate endpoint accessible via the API call gemini-3.1-pro-preview-customtools. This endpoint is better at prioritizing your custom tools (for example, view_file or search_code).\n\nPlease note that while gemini-3.1-pro-preview-customtools is optimized for agent workflows that use custom tools and Bash, you may experience quality fluctuations in some use cases that cannot benefit from these tools.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","web","deepsearch","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.2,"input":2,"output":12,"tiers":[{"cache_read":0.4,"input":4,"output":18,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.1-pro-preview-search","name":"gemini-3.1-pro-preview-search","display_name":"gemini-3.1-pro-preview-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":2,"output":12,"cache_read":0.2},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini-3.1-pro-preview-search integrates Google's official search functionality; the search feature incurs an additional separate fee log directly incorporated into the scoring, but the log details are not displayed; this will be fixed in the future to show the details; it only supports OpenAI-compatible format calls and does not support the Gemini SDK; for the Gemini native SDK, please directly set the official search parameters.","typeHints":["llm"],"features":["thinking","web","deepsearch","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.2,"input":2,"output":12,"tiers":[{"cache_read":0.4,"input":4,"output":18,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gpt-5.4-mini","name":"gpt-5.4-mini","display_name":"gpt-5.4-mini","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.4 mini is a faster, more efficient model that inherits the advantages of GPT-5.4 and is specifically optimized for high-volume workloads.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web"],"inputModalities":["text","image"],"pricing":{"cache_read":0.075,"input":0.75,"output":4.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-nano","name":"gpt-5.4-nano","display_name":"gpt-5.4-nano","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.4 nano is designed for tasks where speed and cost are most important, such as classification, data extraction, ranking, and sub-agent scenarios.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking","web"],"inputModalities":["text","image"],"pricing":{"cache_read":0.02,"input":0.2,"output":1.25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3.5-plus","name":"qwen3.5-plus","display_name":"qwen3.5-plus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.1096,"output":0.6576,"cache_read":0.01096},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.01096,"cache_write":0.137,"input":0.1096,"output":0.6576,"tiers":[{"cache_read":0.0274,"cache_write":0.3425,"input":0.274,"output":1.644,"tier":{"size":128000,"type":"context"}},{"cache_read":0.0548,"cache_write":0.685,"input":0.548,"output":3.288,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-122b-a10b","name":"qwen3.5-122b-a10b","display_name":"qwen3.5-122b-a10b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.1126,"output":0.9008},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"input":0.1126,"output":0.9008,"tiers":[{"input":0.2818,"output":2.2544,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-27b","name":"qwen3.5-27b","display_name":"qwen3.5-27b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.0846,"output":0.6768},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"input":0.0846,"output":0.6768,"tiers":[{"input":0.2536,"output":2.0288,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-35b-a3b","name":"qwen3.5-35b-a3b","display_name":"qwen3.5-35b-a3b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.0564,"output":0.4512},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"input":0.0564,"output":0.4512,"tiers":[{"input":0.2254,"output":1.8032,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-397b-a17b","name":"qwen3.5-397b-a17b","display_name":"qwen3.5-397b-a17b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.1644,"output":0.9864},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen 3.5 native vision-language Plus model is built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In multiple task evaluations, the 3.5 series has demonstrated outstanding performance comparable to current leading frontier models, with leapfrog improvements over the 3 series in both pure-text and multimodal capabilities. This model version is functionally equivalent to the snapshot model qwen3.5-plus-2026-02-15.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"input":0.1644,"output":0.9864,"tiers":[{"input":0.411,"output":2.466,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3.5-flash","name":"qwen3.5-flash","display_name":"qwen3.5-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.0282,"output":0.282,"cache_read":0.00282},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"The Qwen3.5 native vision-language Flash series models are designed with a hybrid architecture that integrates linear attention mechanisms and sparse mixture-of-experts models, achieving higher inference efficiency. Compared with the 3 series, the models deliver leapfrog improvements in both pure-text and multimodal performance; they respond quickly and combine inference speed with high performance.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","web","long_context","thinking"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.00282,"cache_write":0.03525,"input":0.0282,"output":0.282,"tiers":[{"cache_read":0.01126,"cache_write":0.14075,"input":0.1126,"output":1.126,"tier":{"size":128000,"type":"context"}},{"cache_read":0.0169,"cache_write":0.21125,"input":0.169,"output":1.69,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-5.3-chat-latest","name":"gpt-5.3-chat-latest","display_name":"gpt-5.3-chat-latest","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":128000,"output":128000},"metadata":{"description":"GPT-5.3Chat refers to the GPT-5.3 snapshot currently used in ChatGPT and is optimized for conversational use cases. While GPT-5.2 is recommended for most API applications, GPT-5.3Chat is ideal for testing the latest improvements in chat-based interactions.","typeHints":["llm"],"features":["function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.175,"input":1.75,"output":14},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.3-codex","name":"gpt-5.3-codex","display_name":"gpt-5.3-codex","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.3-Codex is optimized for agentic coding tasks in Codex or similar environments. GPT-5.3-Codex supports low, medium, high, and xhigh reasoning effort settings. If you want to learn more about prompting GPT-5.3-Codex, refer to our dedicated guide.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.175,"input":1.75,"output":14},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"claude-sonnet-4-6-think","name":"claude-sonnet-4-6-think","display_name":"claude-sonnet-4-6-think","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":3,"output":15,"cache_read":0.3},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude sonnet 4.6 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, we provide the claude-sonnet-4-6-think model, which has reasoning mode pre-enabled and a default 32k-token context window, allowing it to be called directly via the OpenAI unified API.\nClaude sonnet 4.5 Think is a reasoning-focused variant of Claude sonnet 4.6 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis. Aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude sonnet 4.6 model, making it well suited for complex engineering problem decomposition, multi-stage planning, and logic-intensive analysis.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"coding-xiaomi-mimo-v2-omni","name":"coding-xiaomi-mimo-v2-omni","display_name":"coding-xiaomi-mimo-v2-omni","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.08,"output":0.4,"cache_read":0.016},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.016,"input":0.08,"output":0.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-xiaomi-mimo-v2-pro","name":"coding-xiaomi-mimo-v2-pro","display_name":"coding-xiaomi-mimo-v2-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.6,"cache_read":0.04},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.04,"input":0.2,"output":0.6,"tiers":[{"cache_read":0.08,"input":0.4,"output":1.2,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-2-0-pro","name":"doubao-seed-2-0-pro","display_name":"doubao-seed-2-0-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.4958,"output":2.479,"cache_read":0.09916},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao flagship all-purpose general model, targeting complex reasoning and long-chain task execution scenarios in the Agent era. It emphasizes multimodal understanding, long-context reasoning, structured generation, and tool-augmented execution. It excels at handling complex instructions and multi-constraint execution, reliably addressing multi-step complex planning, intricate image-text reasoning, video content understanding, and high-difficulty analysis scenarios.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.09916,"input":0.4958,"output":2.479,"tiers":[{"cache_read":0.14872,"input":0.7436,"output":3.718,"tier":{"size":32000,"type":"context"}},{"cache_read":0.29744,"input":1.4872,"output":7.436,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.4-high","name":"gpt-5.4-high","display_name":"gpt-5.4-high","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2.5,"output":15,"cache_read":0.25},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-5.4 supports configurable reasoning effort only through the /responses endpoint. To make higher-intensity reasoning available directly via the /chat interface, GPT-5.4-High is provided as a reasoning-enhanced variant of GPT-5.4 with reasoning_effort preset to high. It is designed for tasks that require deeper analysis, stronger result consistency, and greater controllability. By applying more aggressive reasoning strategies and more effective use of extended context, the model delivers clearer and more reliable responses, making it well suited for complex agent workflows, long-chain decision-making, and reliability-critical advanced applications.","typeHints":["llm"],"features":["thinking","function_calling","web","structured_outputs","tools"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.25,"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-low","name":"gpt-5.4-low","display_name":"gpt-5.4-low","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2.5,"output":15,"cache_read":0.25},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"GPT-5.4 supports configuring reasoning strength only through the /responses endpoint. To make lower-overhead reasoning available directly in the /chat endpoint, the GPT-5.4-Low model is provided. This model is based on GPT-5.4 with reasoning_effort preset to low. This model is designed for use cases that are sensitive to response latency and cost. By adopting a lighter reasoning strategy, it delivers stable responses with lower latency and higher throughput. It is well suited for high-concurrency conversations, real-time interactions, basic Q&A, and scenarios where deep reasoning is not required.","typeHints":["llm"],"features":["thinking","function_calling","web","structured_outputs","tools"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.25,"input":2.5,"output":15,"tiers":[{"cache_read":0.5,"input":5,"output":22.5,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-pro","name":"gpt-5.4-pro","display_name":"gpt-5.4-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":30,"output":180},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"Please note: this model is extremely expensive and very slow. If a request fails due to network issues, you may still be charged heavily; we cannot refund charges incurred by requests to this model.\nGPT-5.4 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.4 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeout, please set a longer timeout duration. It is recommended to use this under good network conditions.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"size":272000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qwen3-coder-next","name":"qwen3-coder-next","display_name":"qwen3-coder-next","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.137,"output":0.548},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen3 series is a next-generation code-generation model with results close to Qwen3-Coder-Plus while offering superior performance. The model is optimized for repository-level understanding, supports multi-turn tool interactions, and improves compatibility with agentic coding tools.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.137,"output":0.548,"tiers":[{"input":0.2054,"output":0.8216,"tier":{"size":32000,"type":"context"}},{"input":0.3424,"output":1.3696,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"xiaomi-mimo-v2-omni-free","name":"xiaomi-mimo-v2-omni-free","display_name":"xiaomi-mimo-v2-omni-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"xiaomi-mimo-v2-omni-free is the open free version of xiaomi-mimo-v2-omni.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["web"],"inputModalities":["text","image","video","audio"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"xiaomi-mimo-v2-pro-free","name":"xiaomi-mimo-v2-pro-free","display_name":"xiaomi-mimo-v2-pro-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"xiaomi-mimo-v2-pro-free is the open free version of xiaomi-mimo-v2-pro.  To maintain reliable service, each account is limited to 5 requests per minute, 500 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["web"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"xiaomi-mimo-v2.5-free","name":"xiaomi-mimo-v2.5-free","display_name":"xiaomi-mimo-v2.5-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"xiaomi-mimo-v2.5-free is the open free version of xiaomi-mimo-v2.5.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["web"],"inputModalities":["text","image","video","audio"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"xiaomi-mimo-v2.5-pro-free","name":"xiaomi-mimo-v2.5-pro-free","display_name":"xiaomi-mimo-v2.5-pro-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"xiaomi-mimo-v2.5-pro-free is the open free version of xiaomi-mimo-v2.5-pro.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["web"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"coding-glm-5.1","name":"coding-glm-5.1","display_name":"coding-glm-5.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22},"limit":{"context":200000,"output":200000},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-6","name":"claude-opus-4-6","display_name":"claude-opus-4-6","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Opus 4.6 is Anthropic’s latest state-of-the-art reasoning model. It features an adaptive “thinking” mode that dynamically decides when to think and how much to think. At the default effort level (high), Claude will almost always engage in thinking. At lower effort levels, it may skip thinking for simple problems.\n ⚠️ The minimum cache token for claude-opus-4-6 has been increased from 1,024 to 4,096 tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"coding-glm-5.1-free","name":"coding-glm-5.1-free","display_name":"coding-glm-5.1-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":200000,"output":200000},"metadata":{"description":"coding-glm-5.1-free is the open and free version of coding-glm-5.1.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2.7-free","name":"coding-minimax-m2.7-free","display_name":"coding-minimax-m2.7-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":204800,"output":204800},"metadata":{"description":"coding-minimax-m2.7-free is a free and open version offered by AIHubMix specifically for MiniMax users.  To maintain reliable service, each account is limited to 5 requests per minute, 100 requests per day, and 1 million tokens per day.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-5v-turbo","name":"glm-5v-turbo","display_name":"glm-5v-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.7042,"output":3.09848,"cache_read":0.169008},"limit":{"context":200000,"output":200000},"metadata":{"description":"GLM-5V-Turbo is Zhipu's first multimodal coding foundation model, built for visual programming tasks. It can natively handle multimodal inputs such as images, videos, and text, and is adept at long-horizon planning, complex programming, and action execution; deeply adapted to Agent workflows, it can collaborate closely with agents like Claude Code and OpenClaw to complete the full closed loop of \"understand the environment → plan actions → execute tasks.\"","typeHints":["llm"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.169008,"input":0.7042,"output":3.09848,"tiers":[{"cache_read":0.253402,"input":0.986,"output":3.662004,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"minimax-m2.7","name":"minimax-m2.7","display_name":"minimax-m2.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2958,"output":1.1832,"cache_read":0.05916},"limit":{"context":204800,"output":204800},"metadata":{"description":"MiniMax M2.7 can autonomously build complex Agent Harnesses and, leveraging capabilities such as Agent Teams, complex Skills, and the Tool Search tool, complete highly complex productivity tasks.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.05916,"input":0.2958,"output":1.1832},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-seed-2-0-code-preview","name":"doubao-seed-2-0-code-preview","display_name":"doubao-seed-2-0-code-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.4822,"output":2.411,"cache_read":0.09644},"limit":{"context":256000,"output":256000},"metadata":{"description":"The Doubao 2.0 series is a coding model optimized for real programming environments, capable of reliably invoking tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports using Skills and can work with various custom skills.","typeHints":["llm"],"features":["thinking","web","tools","function_calling"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.09644,"input":0.4822,"output":2.411,"tiers":[{"cache_read":0.144656,"input":0.72328,"output":3.6164,"tier":{"size":32000,"type":"context"}},{"cache_read":0.28932,"input":1.4466,"output":7.233,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-2-0-lite-260215","name":"doubao-seed-2-0-lite-260215","display_name":"doubao-seed-2-0-lite-260215","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.09041,"output":0.54246,"cache_read":0.018082},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao  Coding model optimized for real-world programming environments that can reliably invoke tools in common IDEs such as Claude Code. The model is specially optimized for frontend capabilities and performs well with common frontend frameworks. The model supports Skills and can work with various custom skills.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.018082,"input":0.09041,"output":0.54246,"tiers":[{"cache_read":0.027123,"input":0.135616,"output":0.813696,"tier":{"size":32000,"type":"context"}},{"cache_read":0.054246,"input":0.271232,"output":1.627392,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-flash-preview","name":"gemini-3-flash-preview","display_name":"gemini-3-flash-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.5,"output":3,"cache_read":0.05},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-3-flash-preview is Google's latest released, most balanced model, excelling in speed, scale, and cutting-edge intelligence.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.05,"input":0.5,"output":3},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3-flash-preview-search","name":"gemini-3-flash-preview-search","display_name":"gemini-3-flash-preview-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.5,"output":3,"cache_read":0.05},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini-3-flash-preview-search integrates Google's official search functionality; the search feature incurs an additional separate fee log directly incorporated into the scoring, but the log details are not displayed; this will be fixed in the future to show the details; it only supports OpenAI-compatible format calls and does not support the Gemini SDK; for the Gemini native SDK, please directly set the official search parameters.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.05,"input":0.5,"output":3},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-5-turbo","name":"glm-5-turbo","display_name":"glm-5-turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.2,"output":3.9996,"cache_read":0.24},"limit":{"context":204800,"output":204800},"metadata":{"description":"GLM-5-Turbo is a foundational model deeply optimized for the OpenClaw scenario. From the training stage it has been specifically optimized for the core requirements of OpenClaw tasks, enhancing key capabilities such as tool invocation, instruction following, scheduled and persistent tasks, and long-chain execution.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.24,"input":1.2,"output":3.9996},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-6-think","name":"claude-opus-4-6-think","display_name":"claude-opus-4-6-think","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Claude Opus 4.6 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, we provide the claude-opus-4-6-think model, which has reasoning mode pre-enabled and a default 32k-token context window, allowing it to be called directly via the OpenAI unified API.\nClaude Opus 4.5 Think is a reasoning-focused variant of Claude Opus 4.6 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis. Aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude Opus 4.6 model, making it well suited for complex engineering problem decomposition, multi-stage planning, and logic-intensive analysis.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"coding-glm-5-free","name":"coding-glm-5-free","display_name":"coding-glm-5-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":200000,"output":200000},"metadata":{"description":"coding-glm-5-free is the open and free version of coding-glm-5. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5-turbo-free","name":"coding-glm-5-turbo-free","display_name":"coding-glm-5-turbo-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":204800,"output":204800},"metadata":{"description":"coding-glm-5-turbo-free is the open and free version of coding-glm-5-turbo. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 100 requests per day, and a daily token allowance of 1 million.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2.5-free","name":"coding-minimax-m2.5-free","display_name":"coding-minimax-m2.5-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":204800,"output":204800},"metadata":{"description":"coding-minimax-m2.5-free is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute, 100 total requests per day, and a daily quota of 1 million tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cc-glm-5.1","name":"cc-glm-5.1","display_name":"cc-glm-5.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22},"limit":{"context":200000,"output":200000},"metadata":{"description":"Supports Claude native interface, can be directly requested in Claude Code.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-5","name":"claude-opus-4-5","display_name":"claude-opus-4-5","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":200000,"output":200000},"metadata":{"description":"Claude Opus 4.5 is Anthropic’s latest frontier reasoning model, optimized for complex engineering, agentic workflows, and long-horizon computer use. It features strong multimodal capabilities, improved resistance to prompt injection, and a new Verbosity parameter to control token efficiency. With advanced tool use, extended context, and multi-agent support, Opus 4.5 excels in autonomous research, debugging, planning, and spreadsheet/browser operations.\n⚠️ The minimum cache token for claude-opus-4-5 has been increased from 1,024 to 4,096 tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-opus-4-5-think","name":"claude-opus-4-5-think","display_name":"claude-opus-4-5-think","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":200000,"output":200000},"metadata":{"description":"Claude Opus 4.5 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, we provide the claude-opus-4-5-think model, which has reasoning mode pre-enabled and a default 32k-token context window, allowing it to be called directly via the OpenAI unified API.\nClaude Opus 4.5 Think is a reasoning-focused variant of Claude Opus 4.5 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis. Aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude Opus 4.5 model, making it well suited for complex engineering problem decomposition, multi-stage planning, and logic-intensive analysis.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"embed-v-4-0","name":"embed-v-4-0","display_name":"embed-v-4-0","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.12,"output":0},"limit":{"context":128000,"output":128000},"metadata":{"description":"Cohere’s Embed 4 is a multilingual multimodal embedding model. It is capable of transforming different modalities such as images, texts, and interleaved images and texts into a single vector representation. Embed 4 offers state-of-the-art performance across all modalities (texts, images, interleaved texts and image) and in both English and multilingual settings. Embed 4 supports a 128k context length and an images can have a maximum of 2MM pixels.","typeHints":["embedding"],"inputModalities":["text","image"],"pricing":{"input":0.12,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"ernie-image-turbo","name":"ernie-image-turbo","display_name":"ernie-image-turbo","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"description":"The Ernie-image-Turbo model is an 8-step distilled version of the Ernie-image model, also with 8 billion parameters, offering a 6x speedup compared to pre-distillation, and is suitable for low-latency, local/on-device scenarios.","typeHints":["image_generation"],"source":"public-provider-conf"},"vision":false},{"id":"mimo-v2-omni","name":"mimo-v2-omni","display_name":"mimo-v2-omni","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.44,"output":2.2,"cache_read":0.088},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"MiMo-V2-Omni is designed for complex real-world multimodal interaction and execution scenarios. We've built an all-modal foundation from the ground up that fuses text, vision, and speech, and use a unified architecture to deeply bind \"perception\" and \"action.\" This not only breaks the traditional models' limitation of emphasizing understanding over execution, but also natively equips the model with multimodal perception, tool invocation, function execution, and GUI operation capabilities. MiMo-V2-Omni can seamlessly integrate with major agent frameworks, achieving a leap from understanding to manipulation and significantly lowering the barrier to deploying full-modal agents.","typeHints":["llm"],"features":["web"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.088,"input":0.44,"output":2.2},"source":"public-provider-conf"},"vision":true},{"id":"mimo-v2-pro","name":"mimo-v2-pro","display_name":"mimo-v2-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":1.1,"output":3.3,"cache_read":0.22},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Xiaomi MiMo-V2-Pro is built for high-intensity agent work scenarios in the real world. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M-token context length. On top of a powerful model foundation, we continuously scale compute across broader agent scenarios, further expanding the intelligent action space and achieving significant generalization from Coding to Claw.","typeHints":["llm"],"features":["web"],"inputModalities":["text"],"pricing":{"cache_read":0.22,"input":1.1,"output":3.3,"tiers":[{"cache_read":0.44,"input":2.2,"output":6.6,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"cohere-command-a","name":"cohere-command-a","display_name":"cohere-command-a","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":2.5,"output":10},"limit":{"context":256000,"output":256000},"metadata":{"description":"Command A is Cohere most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":2.5,"output":10},"source":"public-provider-conf"},"vision":false},{"id":"cc-minimax-m3","name":"cc-minimax-m3","display_name":"cc-minimax-m3","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":true},{"id":"coding-minimax-m3","name":"coding-minimax-m3","display_name":"coding-minimax-m3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":1000000,"output":1000000},"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5","name":"coding-glm-5","display_name":"coding-glm-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22},"limit":{"context":200000,"output":200000},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-5-turbo","name":"coding-glm-5-turbo","display_name":"coding-glm-5-turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22},"limit":{"context":204800,"output":204800},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.7","name":"glm-4.7","display_name":"glm-4.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.273974,"output":1.095896,"cache_read":0.054795},"limit":{"context":200000,"output":200000},"metadata":{"description":"GLM-4.7 is Zhiyuan's latest flagship model. GLM-4.7 enhances coding capabilities, long-range task planning, and tool collaboration for Agentic Coding scenarios, achieving leading performance among open-source models on several current public benchmarks. It features improved general capabilities, with responses that are more concise and natural, and writing that is more immersive. When executing complex agent tasks and tool usage, it follows instructions more strictly, with further improvements in the frontend aesthetics of Artifacts and Agentic Coding as well as the efficiency of completing long-range tasks.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.054795,"input":0.273974,"output":1.095896,"tiers":[{"cache_read":0.109589,"input":0.547946,"output":2.191784,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"veo-3.1-lite-generate-preview","name":"veo-3.1-lite-generate-preview","display_name":"veo-3.1-lite-generate-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Veo 3.1 is Google's state-of-the-art model for generating high-fidelity, 8-second 720p , 1080p videos featuring stunning realism and natively generated audio.","typeHints":["video"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"glm-4.7-flash-free","name":"glm-4.7-flash-free","display_name":"glm-4.7-flash-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":200000,"output":200000},"metadata":{"description":"The glm-4.7-flash free model has usage restrictions to ensure stable service operation: a maximum of 5 requests per minute, no more than 500 requests per day, and a daily usage quota of 1 million tokens.","typeHints":["llm"],"features":["thinking","tools","structured_outputs","function_calling"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-4.7-free","name":"coding-glm-4.7-free","display_name":"coding-glm-4.7-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":200000,"output":200000},"metadata":{"description":"coding-glm-4.7-free is the open and free version of coding-glm-4.7. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 500 requests per day, and a daily token allowance of 1 million.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seedance-1-5-pro-251215","name":"doubao-seedance-1-5-pro-251215","display_name":"doubao-seedance-1-5-pro-251215","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Doubao video generation model Seedance 1.5 Pro, as a world-leading video generation model, can produce video content with high-precision audio–visual synchronization. It supports multi-person, multi-language dialogue and comprehensively covers ambient sounds, action sounds, synthesized sounds, musical instrument sounds, background sounds, and human voices. It supports start-and-end frames to achieve film-level narrative effects, meeting the advanced creative needs of film, animated series, e-commerce, and advertising.","typeHints":["video"],"inputModalities":["image","text"],"source":"public-provider-conf"},"vision":true},{"id":"doubao-seedance-1-0-pro-250528","name":"doubao-seedance-1-0-pro-250528","display_name":"doubao-seedance-1-0-pro-250528","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedance 1.0 Pro is a foundational video-generation model that supports multi-shot storytelling and excels across multiple dimensions. It has made breakthroughs in semantic understanding and instruction-following, enabling the generation of 1080P HD videos with smooth motion, rich detail, diverse styles, and cinematic aesthetics.","typeHints":["video"],"inputModalities":["image","text"],"source":"public-provider-conf"},"vision":true},{"id":"doubao-seedance-1-0-pro-fast-251015","name":"doubao-seedance-1-0-pro-fast-251015","display_name":"doubao-seedance-1-0-pro-fast-251015","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedance 1.0 Pro Fast is a comprehensive model that delivers rock-bottom prices and peak performance, striking an outstanding balance among video generation quality, speed, and cost. It inherits the core advantages of Seedance 1.0 Pro while increasing generation speed and offering more competitive pricing, providing creators with dual optimization of efficiency and cost.","typeHints":["video"],"inputModalities":["image","text"],"source":"public-provider-conf"},"vision":true},{"id":"gemini-3-pro-image-preview","name":"gemini-3-pro-image-preview","display_name":"gemini-3-pro-image-preview","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":12,"cache_read":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemini-3-Pro-Image-Preview (Nano Banana Pro) is a high-performance image generation and editing model built on Gemini 3 Pro. It delivers enhanced multimodal understanding and real-world semantic reasoning, enabling fast creation of well-structured visual content such as infographics, product sketches, and multi-subject scenes. It can also leverage real-time knowledge through Search grounding. The model excels in text rendering, consistent multi-image blending, and identity preservation, while offering fine-grained creative controls like localized edits, lighting and focus adjustments, camera transformations, and flexible aspect ratios. It’s ideal for rapid design, concept previews, product visualization, and everyday image generation workflows.","typeHints":["image_generation","llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":2,"output":12},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-embedding-2","name":"gemini-embedding-2","display_name":"gemini-embedding-2","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","audio","video"]},"cost":{"input":0.2,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Google's first multimodal embedding model .","typeHints":["embedding"],"inputModalities":["text","image","audio","video"],"pricing":{"input":0.2,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.2-codex","name":"gpt-5.2-codex","display_name":"gpt-5.2-codex","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.2-Codex is an upgraded version of GPT-5.2, optimized for agentic coding tasks in Codex and similar execution environments. The model is specifically enhanced for code generation, modification, refactoring, and automated execution workflows, enabling more efficient participation in multi-step, tool-driven programming processes. GPT-5.2-Codex supports low, medium, high, and xhigh reasoning effort settings, allowing flexible trade-offs between latency, reasoning depth, and token usage depending on task complexity.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.175,"input":1.75,"output":14},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepinfra-gemma-4-26b-a4b-it","name":"deepinfra-gemma-4-26b-a4b-it","display_name":"deepinfra-gemma-4-26b-a4b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.088,"output":0.385,"cache_read":0.011},"limit":{"context":262100,"output":262100},"metadata":{"description":"A Mixture-of-Experts model that activates only 4B parameters per inference,delivering high-performance reasoning with a fraction of the memory cost - idealfor cost-efficient, high-throughput server deployments.","typeHints":["llm"],"pricing":{"cache_read":0.011,"input":0.088,"output":0.385},"source":"public-provider-conf"},"vision":false},{"id":"doubao-seedream-5.0-lite","name":"doubao-seedream-5.0-lite","display_name":"doubao-seedream-5.0-lite","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-Seedream-5.0-lite is the latest image-creation model released by ByteDance. For the first time, the model includes an online retrieval capability, allowing it to integrate real-time web information and improve the timeliness of generated images. At the same time, the model’s intelligence has been further upgraded, enabling it to accurately parse complex instructions and visual content. In addition, the model has been enhanced in terms of breadth of world knowledge, reference consistency, and generation quality in professional scenarios, better meeting enterprise-level visual-creation needs.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-1.5","name":"gpt-image-1.5","display_name":"gpt-image-1.5","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":10},"limit":{"context":8192,"output":8192},"metadata":{"description":"GPT Image 1.5 is a new image generation model powered by OpenAI’s flagship visual capabilities, comprehensively upgraded for high-quality creative and production workflows. It delivers significant improvements in instruction understanding, fine-grained image editing, and detail preservation, while achieving up to 4× faster generation compared to previous versions — reducing latency without compromising quality.\n\nGPT Image 1.5 is well suited for image generation, precise visual editing, and professional content creation, balancing performance with efficiency.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":5,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"doubao-seed-2-1-pro-260628","name":"doubao-seed-2-1-pro-260628","display_name":"doubao-seed-2-1-pro-260628","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.9295,"output":4.6475,"cache_read":0.1859},"limit":{"context":256000,"output":256000},"metadata":{"description":"A new generation of large models moving toward production-grade intelligence, comprehensively upgrading coding, agent, and multimodal capabilities with stronger autonomous planning, long-horizon execution, and dynamic recovery abilities to handle real, complex enterprise tasks.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.1859,"input":0.9295,"output":4.6475},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.2","name":"gpt-5.2","display_name":"gpt-5.2","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.2 is an advanced general-purpose model that improves on GPT-5.1 with more reliable, flexible, and user-friendly interactions. It delivers clearer responses, stronger instruction-following, and adaptive reasoning that scales from simple requests to complex, multi-step tasks. With enhanced control over tone and structure and support for extended context, GPT-5.2 is well suited for agent workflows, analysis, coding, and cross-domain applications.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs","web","tools"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.175,"input":1.75,"output":14},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-chat-latest","name":"gpt-5.2-chat-latest","display_name":"gpt-5.2-chat-latest","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":128000,"output":128000},"metadata":{"description":"GPT-5.2Chat refers to the GPT-5.2 snapshot currently used in ChatGPT and is optimized for conversational use cases. While GPT-5.2 is recommended for most API applications, GPT-5.2Chat is ideal for testing the latest improvements in chat-based interactions.","typeHints":["llm"],"features":["function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.175,"input":1.75,"output":14},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.2-high","name":"gpt-5.2-high","display_name":"gpt-5.2-high","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.2 supports configurable reasoning effort only through the /responses endpoint. To make higher-intensity reasoning available directly via the /chat interface, GPT-5.2-High is provided as a reasoning-enhanced variant of GPT-5.2 with reasoning_effort preset to high. It is designed for tasks that require deeper analysis, stronger result consistency, and greater controllability. By applying more aggressive reasoning strategies and more effective use of extended context, the model delivers clearer and more reliable responses, making it well suited for complex agent workflows, long-chain decision-making, and reliability-critical advanced applications.","typeHints":["llm"],"features":["thinking","function_calling","web","structured_outputs","tools"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.175,"input":1.75,"output":14},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-low","name":"gpt-5.2-low","display_name":"gpt-5.2-low","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.2 supports configuring reasoning strength only through the /responses endpoint. To make lower-overhead reasoning available directly in the /chat endpoint, the GPT-5.2-Low model is provided. This model is based on GPT-5.2 with reasoning_effort preset to low. This model is designed for use cases that are sensitive to response latency and cost. By adopting a lighter reasoning strategy, it delivers stable responses with lower latency and higher throughput. It is well suited for high-concurrency conversations, real-time interactions, basic Q&A, and scenarios where deep reasoning is not required.","typeHints":["llm"],"features":["thinking","function_calling","web","structured_outputs","tools"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.175,"input":1.75,"output":14},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-pro","name":"gpt-5.2-pro","display_name":"gpt-5.2-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":21,"output":168,"cache_read":2.1},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.2 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5.2 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeout, please set a longer timeout duration. It is recommended to use this under good network conditions.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":2.1,"input":21,"output":168},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1","name":"gpt-5.1","display_name":"gpt-5.1","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5 is OpenAI’s most advanced language model, designed for complex tasks that require step-by-step reasoning, precise instruction following, and high reliability. It improves reasoning, code generation, and prompt understanding—including test-time routing and intent cues like “think hard about this”—while reducing hallucination and sycophancy.","typeHints":["llm"],"features":["thinking","web","tools","deepsearch","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.125,"input":1.25,"output":10},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-max","name":"gpt-5.1-codex-max","display_name":"gpt-5.1-codex-max","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.1-Codex-Max is a frontier programming model built for the agent-driven era. Powered by an upgraded core reasoning architecture, it is specially trained for complex agentic tasks in software engineering, mathematics, and scientific research. It delivers faster performance, greater stability, and higher token efficiency across the entire development lifecycle, including code generation, refactoring, debugging, and engineering collaboration. With native support for multiple context windows and a built-in compaction mechanism, the model can coherently process millions of tokens within a single task.","typeHints":["llm"],"features":["function_calling","structured_outputs","thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.125,"input":1.25,"output":10},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"doubao-seed-1-8","name":"doubao-seed-1-8","display_name":"doubao-seed-1-8","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.10959,"output":0.273975,"cache_read":0.021918},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao's strongest multimodal Agent model Seed1.8 has powerful multimodal capabilities, supports image and text input, and can efficiently and accurately complete tasks in scenarios such as information retrieval, code generation, GUI interaction, and complex workflows, meeting increasingly diverse technical demands.","typeHints":["llm"],"features":["thinking","web","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.021918,"input":0.10959,"output":0.273975,"tiers":[{"cache_read":0.021915,"input":0.1644,"output":2.191995,"tier":{"size":32000,"type":"context"}},{"cache_read":0.021918,"input":0.32876,"output":3.2876,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.1-chat-latest","name":"gpt-5.1-chat-latest","display_name":"gpt-5.1-chat-latest","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":128000,"output":128000},"metadata":{"description":"GPT-5.1 Chat refers to the GPT-5.1 snapshot currently used in ChatGPT and is optimized for conversational use cases. While GPT-5.1 is recommended for most API applications, GPT-5.1 Chat is ideal for testing the latest improvements in chat-based interactions.","typeHints":["llm"],"features":["function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.125,"input":1.25,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.1-codex","name":"gpt-5.1-codex","display_name":"gpt-5.1-codex","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.1-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar environments. It's available in the Responses API only and the underlying model snapshot will be regularly updated.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.125,"input":1.25,"output":10},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-mini","name":"gpt-5.1-codex-mini","display_name":"gpt-5.1-codex-mini","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.25,"output":2,"cache_read":0.025},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5.1 Codex mini is a smaller, more cost-effective, less-capable version of GPT-5.1-Codex.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.025,"input":0.25,"output":2},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4.20-multi-agent-0309","name":"grok-4.20-multi-agent-0309","display_name":"grok-4.20-multi-agent-0309","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok 4.20 is our newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":2,"output":6},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistral-large-3","name":"mistral-large-3","display_name":"mistral-large-3","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.5,"output":1.5},"limit":{"context":256000,"output":256000},"metadata":{"description":"Mistral Large 3 is a MoE model with 67.5B total parameters and 41B active parameters, supporting a 256K-token context window. Trained from scratch on 3,000 NVIDIA H200 GPUs, it is one of the strongest permissively licensed open-weight models available.\n\nDesigned for advanced reasoning and long-context understanding, Mistral Large 3 delivers performance on par with the best instruction-tuned open-weight models for general-purpose tasks, while also offering image understanding capabilities. Its multilingual strengths are particularly notable for non-English/Chinese languages, making it well-suited for global applications.\n\nTypical use cases include enterprise assistants, multilingual customer support, content generation and editing, data analysis over long documents, code assistance, and research workflows that require handling large corpora or complex instructions. With its MoE architecture, Mistral Large 3 balances strong performance with efficient inference, providing a versatile backbone for building reliable, production-grade AI systems.","typeHints":["llm"],"features":["function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.5,"output":1.5},"source":"public-provider-conf"},"vision":true},{"id":"claude-haiku-4-5","name":"claude-haiku-4-5","display_name":"claude-haiku-4-5","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.1,"output":5.5,"cache_read":0.11},"limit":{"context":200000,"output":200000},"metadata":{"description":"Claude Haiku 4.5 is a fast, affordable, and highly capable AI model, excelling at coding and agentic tasks. Its combination of speed and low cost makes it ideal for powering real-time applications like chatbots, high-volume free services, and specialized \"sub-agents\" for complex tasks in coding, finance, and research. It can also handle common business tasks like creating office documents and assisting with strategy and analysis.\n⚠️ The minimum cache token for claude-haiku-4-5 has been increased from 1,024 to 4,096 tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.11,"cache_write":1.375,"input":1.1,"output":5.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-4-5","name":"claude-sonnet-4-5","display_name":"claude-sonnet-4-5","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":3.3,"output":16.5,"cache_read":0.33},"limit":{"context":200000,"output":200000},"metadata":{"description":"Sonnet 4.5 is the best model in the world for agents, coding, and computer usage. It is also our most accurate and detailed model for long-running tasks, with enhanced knowledge in coding, finance, and cybersecurity.  \nThis model supports a thinking parameter to enable thinking requests in Claude mode.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.33,"cache_write":4.125,"input":3.3,"output":16.5,"tiers":[{"cache_read":0.66,"cache_write":8.25,"input":6.6,"output":24.75,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-sonnet-4-5-think","name":"claude-sonnet-4-5-think","display_name":"claude-sonnet-4-5-think","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":3.3,"output":16.5,"cache_read":0.33},"limit":{"context":200000,"output":200000},"metadata":{"description":"Claude Sonnet 4.5 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, the claude-sonnet-4-5-think model is provided with reasoning mode pre-enabled and a default 64k-token context window, allowing it to be called directly via the OpenAI unified API. Claude Sonnet 4.5 Think is a reasoning-focused variant of Claude Sonnet 4.5 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis; aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude Sonnet 4.5 model, making it well suited for complex problem decomposition, multi-step planning, and logic-intensive analysis.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.33,"cache_write":4.125,"input":3.3,"output":16.5,"tiers":[{"cache_read":0.66,"cache_write":8.25,"input":6.6,"output":24.75,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"cc-glm-5","name":"cc-glm-5","display_name":"cc-glm-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22},"limit":{"context":200000,"output":200000},"metadata":{"description":"Supports Claude native interface, can be directly requested in Claude Code.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cc-glm-5-turbo","name":"cc-glm-5-turbo","display_name":"cc-glm-5-turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22},"limit":{"context":204800,"output":204800},"metadata":{"description":"Supports Claude native interface, can be directly requested in Claude Code.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cloudflare-glm-5.2","name":"cloudflare-glm-5.2","display_name":"cloudflare-glm-5.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":1.4,"output":4.4002,"cache_read":0.2604},"limit":{"context":1000000,"output":1000000},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.2604,"input":1.4,"output":4.4002},"source":"public-provider-conf"},"vision":false},{"id":"grok-4-1-fast-non-reasoning","name":"grok-4-1-fast-non-reasoning","display_name":"grok-4-1-fast-non-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok 4.1 is a new conversational model with significant improvements in real-world usability, delivering exceptional performance in creative, emotional, and collaborative interactions. It is more perceptive to nuanced user intent, more engaging to converse with, and more coherent in personality, while fully preserving its core intelligence and reliability. Built on large-scale reinforcement learning infrastructure, the model is optimized for style, personality, helpfulness, and alignment, and leverages frontier agentic reasoning models as reward evaluators to autonomously assess and iterate on responses at scale, significantly enhancing overall interaction quality.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.05,"input":0.2,"output":0.5},"source":"public-provider-conf"},"vision":true},{"id":"grok-4-1-fast-reasoning","name":"grok-4-1-fast-reasoning","display_name":"grok-4-1-fast-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok 4.1 is a new conversational model with significant improvements in real-world usability, delivering exceptional performance in creative, emotional, and collaborative interactions. It is more perceptive to nuanced user intent, more engaging to converse with, and more coherent in personality, while fully preserving its core intelligence and reliability. Built on large-scale reinforcement learning infrastructure, the model is optimized for style, personality, helpfulness, and alignment, and leverages frontier agentic reasoning models as reward evaluators to autonomously assess and iterate on responses at scale, significantly enhancing overall interaction quality.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.05,"input":0.2,"output":0.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-code-fast-1","name":"grok-code-fast-1","display_name":"grok-code-fast-1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1,"output":2,"cache_read":0.2},"limit":{"context":256000,"output":256000},"metadata":{"description":"Grok 4.1 is a new conversational model with significant improvements in real-world usability, delivering exceptional performance in creative, emotional, and collaborative interactions. It is more perceptive to nuanced user intent, more engaging to converse with, and more coherent in personality, while fully preserving its core intelligence and reliability. Built on large-scale reinforcement learning infrastructure, the model is optimized for style, personality, helpfulness, and alignment, and leverages frontier agentic reasoning models as reward evaluators to autonomously assess and iterate on responses at scale, significantly enhancing overall interaction quality.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":1,"output":2,"tiers":[{"cache_read":0.4,"input":2,"output":2,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"k2.6-code-preview-free","name":"k2.6-code-preview-free","display_name":"k2.6-code-preview-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":262144},"metadata":{"description":"kimi-for-coding-free is a free and open version offered by AIHubMix specifically for Kimi users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute 500 total requests per day, and a daily quota of 1 million tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mimo-v2-flash","name":"mimo-v2-flash","display_name":"mimo-v2-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.1918,"output":0.5754,"cache_read":0.03836},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"MiMo-V2-Flash is a mixture of experts (MoE) language model with a total of 309 billion parameters and 15 billion activated parameters. It is designed for high-speed inference and proxy workflows, adopting a novel hybrid attention architecture and multi-token prediction (MTP), significantly reducing inference costs while achieving state-of-the-art performance.","typeHints":["llm"],"features":["web"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.03836,"input":0.1918,"output":0.5754},"source":"public-provider-conf"},"vision":true},{"id":"musesteamer-air-image","name":"musesteamer-air-image","display_name":"musesteamer-air-image","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"description":"musesteamer-air-image is a text-to-image model developed by the Baidu Search team aimed at providing extreme cost-effectiveness. It can quickly generate clear images with coherent actions based on user prompts, making it easy to convert users' descriptions into images.","typeHints":["image_generation"],"source":"public-provider-conf"},"vision":false},{"id":"gemini-2.5-flash-image","name":"gemini-2.5-flash-image","display_name":"gemini-2.5-flash-image","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.3,"output":2.499,"cache_read":0.03},"limit":{"context":65536,"output":65536},"metadata":{"description":"Gemini 2.5 Flash Image (Nano-Banana) is a state-of-the-art image generation and editing model that enables seamless blending of multiple images into a single composition while maintaining character consistency for rich visual storytelling. It supports precise, targeted image transformations through natural language instructions and leverages built-in world knowledge for both image generation and editing, making it well suited for creative design, content production, advertising, and visual expression workflows.","typeHints":["image_generation","llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"source":"public-provider-conf"},"vision":true},{"id":"qwen3.6-plus-preview-free","name":"qwen3.6-plus-preview-free","display_name":"qwen3.6-plus-preview-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"This model has been removed from the platform.","typeHints":["llm"],"features":["thinking","long_context"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-glm-5-turbo","name":"zai-glm-5-turbo","display_name":"zai-glm-5-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":1.2,"output":3.9996,"cache_read":0.24},"limit":{"context":204800,"output":204800},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.24,"input":1.2,"output":3.9996},"source":"public-provider-conf"},"vision":false},{"id":"gpt-5","name":"gpt-5","display_name":"gpt-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5 is OpenAI’s most advanced general-purpose model, delivering major improvements in reasoning, code quality, and overall user experience. It is optimized for complex tasks that require step-by-step reasoning, precise instruction following, and high accuracy in high-stakes scenarios. The model supports test-time routing and advanced prompt understanding, including user-specified intent such as “think hard about this,” while significantly reducing hallucination and sycophancy and improving performance in coding, writing, and health-related tasks.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.125,"input":1.25,"output":10},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"deepseek-v3.2","name":"deepseek-v3.2","display_name":"deepseek-v3.2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.302,"output":0.453,"cache_read":0.0302},"limit":{"context":163840,"output":163840},"metadata":{"description":"DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse Attention and reinforced reasoning performance, but its core strength lies in powerful agentic capabilities—enabled by large-scale task-synthesis that tightly integrates reasoning with real-world tool use, delivering robust, compliant, and generalizable agent behaviour. Users can toggle deeper reasoning through the reasoning_enabled switch.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.0302,"input":0.302,"output":0.453},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-codex","name":"gpt-5-codex","display_name":"gpt-5-codex","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5-Codex is a version of GPT-5 optimized for autonomous coding tasks in Codex or similar environments. It is only available in the Responses API, and the underlying model snapshots will be updated regularly. https://docs.aihubmix.com/en/api/Responses-API You can also use it in codex-cll; see https://docs.aihubmix.com/en/api/Codex-CLI for using codex-cll through Aihubmix.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.125,"input":1.25,"output":10},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-pro","name":"gpt-5-pro","display_name":"gpt-5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":15,"output":120},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5 pro uses more compute to think harder and provide consistently better answers.\n\nGPT-5 pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests, and other advanced API features in the future. Since GPT-5 pro is designed to tackle tough problems, some requests may take several minutes to finish. To avoid timeouts, try using background mode. As our most advanced reasoning model, GPT-5 pro defaults to (and only supports) reasoning.effort: high. GPT-5 pro does not support code interpreter.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":15,"output":120},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"DeepSeek-V3.1-Think","name":"DeepSeek-V3.1-Think","display_name":"DeepSeek-V3.1-Think","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.56,"output":1.68},"limit":{"context":128000,"output":128000},"metadata":{"description":"Thinking mode of DeepSeek-V3.1;  \nDeepSeek V3.1 is a text generation model provided by DeepSeek, featuring a hybrid reasoning architecture that achieves an effective integration of thinking and non-thinking modes.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.56,"output":1.68},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5-mini","name":"gpt-5-mini","display_name":"gpt-5-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.25,"output":2,"cache_read":0.025},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.025,"input":0.25,"output":2},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-nano","name":"gpt-5-nano","display_name":"gpt-5-nano","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"limit":{"context":400000,"output":400000},"metadata":{"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, designed specifically for developer tools and environments that demand rapid interactions and ultra-low latency. While it offers a more lightweight solution with limited reasoning depth compared to its larger counterparts, GPT-5-Nano excels in core capabilities such as instruction-following and maintaining critical safety features. As the successor to GPT-4.1-nano, it provides an optimal choice for cost-sensitive or real-time applications, where efficiency and speed are paramount. Particularly well-suited for summarization and classification tasks, GPT-5-Nano is a powerful tool for developers needing a swift, reliable AI model for streamlined processes.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.005,"input":0.05,"output":0.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-chat-latest","name":"gpt-5-chat-latest","display_name":"gpt-5-chat-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":128000,"output":128000},"metadata":{"description":"GPT-5 Chat points to the GPT-5 snapshot currently used in ChatGPT. GPT-5 is our next-generation, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.125,"input":1.25,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"claude-opus-4-1","name":"claude-opus-4-1","display_name":"claude-opus-4-1","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":16.5,"output":82.5},"limit":{"context":200000,"output":200000},"metadata":{"description":"Opus 4.1 is an upgraded version of Claude Opus 4, with improvements mainly in agent tasks, practical coding, and reasoning. Compared to Opus 4, there is a slight improvement in software engineering accuracy; Opus 4.1 has higher accuracy at 74.5%.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":16.5,"output":82.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"o3-deep-research","name":"o3-deep-research","display_name":"o3-deep-research","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":10,"output":40,"cache_read":2.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Only supported through requests to the v1/responses interface.\no3-deep-research is OpenAI most advanced model for deep research, designed to tackle complex, multi-step research tasks. It can search and synthesize information from across the internet as well as from your own data—brought in through MCP connectors.","typeHints":["llm"],"pricing":{"cache_read":2.5,"input":10,"output":40},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"kimi-k2.5","name":"kimi-k2.5","display_name":"kimi-k2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.6,"output":3,"cache_read":0.105},"limit":{"context":262144,"output":262144},"metadata":{"description":"Kimi K2.5 is the smartest model of Kimi to date, achieving open-source state-of-the-art (SoTA) performance in Agent, coding, visual understanding, and a series of general intelligent tasks. At the same time, Kimi K2.5 is also the most versatile model of Kimi so far, with a native multimodal architecture design that supports both visual and text input, thinking and non-thinking modes, as well as dialogue and Agent tasks.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.105,"input":0.6,"output":3},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-max-2026-01-23","name":"qwen3-max-2026-01-23","display_name":"qwen3-max-2026-01-23","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.4508,"output":1.8032,"cache_read":0.09016},"limit":{"context":262144,"output":262144},"metadata":{"description":"The snapshot version of the Tongyi Qianwen 3 series Max model is from January 23, 2026. By default, it does not require thinking, but thinking mode can be enabled through the enable_thinking parameter, as detailed in the code example. (After enabling thinking by passing parameters, it becomes: Qwen3-Max-Thinking). This model has a total parameter count exceeding one trillion (1T) and a pre-training data volume of up to 36T Tokens, making it the largest and most powerful reasoning model from Alibaba to date.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.09016,"cache_write":0.5635,"input":0.4508,"output":1.8032,"tiers":[{"cache_read":0.1804,"cache_write":1.1275,"input":0.902,"output":3.608,"tier":{"size":32000,"type":"context"}},{"cache_read":0.27044,"cache_write":1.69025,"input":1.3522,"output":5.4088,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-vl-flash","name":"qwen3-vl-flash","display_name":"qwen3-vl-flash","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.0206,"output":0.206,"cache_read":0.00412},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen3 series of compact visual-understanding models achieves an effective fusion of thinking mode and non-thinking mode, outperforming the open-source Qwen3-VL-30B-A3B with faster response speeds. It comprehensively upgrades image and video understanding, supporting ultra-long contexts such as long videos and long documents, spatial awareness, and universal object recognition; it also possesses visual 2D/3D localization capabilities and is capable of handling complex real-world tasks.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.00412,"input":0.0206,"output":0.206,"tiers":[{"cache_read":0.0082,"input":0.041,"output":0.41,"tier":{"size":32000,"type":"context"}},{"cache_read":0.01644,"input":0.0822,"output":0.822,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-vl-flash-2026-01-22","name":"qwen3-vl-flash-2026-01-22","display_name":"qwen3-vl-flash-2026-01-22","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.0206,"output":0.206},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen3 series of compact visual-understanding models achieves an effective fusion of thinking mode and non-thinking mode, outperforming the open-source Qwen3-VL-30B-A3B with faster response speeds. It comprehensively upgrades image and video understanding, supporting ultra-long contexts such as long videos and long documents, spatial awareness, and universal object recognition; it also possesses visual 2D/3D localization capabilities and is capable of handling complex real-world tasks.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.0206,"output":0.206,"tiers":[{"input":0.041,"output":0.41,"tier":{"size":32000,"type":"context"}},{"input":0.0822,"output":0.822,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-vl-plus","name":"qwen3-vl-plus","display_name":"qwen3-vl-plus","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.137,"output":1.37,"cache_read":0.0274},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Qwen3 series visual understanding model achieves an effective fusion of thinking and non-thinking modes. Its visual agent capabilities reach world-class levels on public test sets such as OS World. This version features comprehensive upgrades in visual coding, spatial perception, and multimodal reasoning; visual perception and recognition abilities are greatly enhanced, supporting ultra-long video understanding.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.0274,"input":0.137,"output":1.37,"tiers":[{"input":0.2054,"output":2.054,"tier":{"size":32000,"type":"context"}},{"input":0.411,"output":4.11,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"cc-minimax-m2.7","name":"cc-minimax-m2.7","display_name":"cc-minimax-m2.7","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":204800,"output":204800},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"cc-minimax-m2.7-highspeed","name":"cc-minimax-m2.7-highspeed","display_name":"cc-minimax-m2.7-highspeed","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":204800,"output":204800},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"minimax-m2.5","name":"minimax-m2.5","display_name":"minimax-m2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.288,"output":1.152},"limit":{"context":204800,"output":204800},"metadata":{"description":"The MiniMax M2.5 is a flagship programming model built for real-world productivity. As a production-grade model natively designed for Agent scenarios, it has achieved state-of-the-art (SOTA) performance in coding, agentic tool use, search, and office work.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.288,"output":1.152},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2.5-highspeed","name":"minimax-m2.5-highspeed","display_name":"minimax-m2.5-highspeed","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.288,"output":1.152},"limit":{"context":204800,"output":204800},"metadata":{"description":"• Same performance as minimax-m2.5\n• Significantly faster inference","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.288,"output":1.152},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mm-minimax-m2.7-highspeed","name":"mm-minimax-m2.7-highspeed","display_name":"mm-minimax-m2.7-highspeed","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":204800,"output":204800},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"coding-minimax-m2.7","name":"coding-minimax-m2.7","display_name":"coding-minimax-m2.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":204800,"output":204800},"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2.7-highspeed","name":"coding-minimax-m2.7-highspeed","display_name":"coding-minimax-m2.7-highspeed","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":204800,"output":204800},"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"cc-minimax-m2.5","name":"cc-minimax-m2.5","display_name":"cc-minimax-m2.5","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":204800,"output":204800},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"cc-minimax-m2.5-highspeed","name":"cc-minimax-m2.5-highspeed","display_name":"cc-minimax-m2.5-highspeed","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":204800,"output":204800},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"coding-minimax-m2.5","name":"coding-minimax-m2.5","display_name":"coding-minimax-m2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":204800,"output":204800},"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2.5-highspeed","name":"coding-minimax-m2.5-highspeed","display_name":"coding-minimax-m2.5-highspeed","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":204800,"output":204800},"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"sora-2","name":"sora-2","display_name":"sora-2","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"description":"Sora-2 is the next-generation text-to-video model evolved from Sora, optimized for higher visual realism, stronger physical consistency, and longer temporal coherence. It delivers more stable character consistency, complex motion rendering, camera control, and narrative continuity, while supporting higher resolutions and minute-level video generation for film production, advertising, virtual content creation, and creative multimedia workflows.","typeHints":["video"],"source":"public-provider-conf"},"vision":false},{"id":"sora-2-pro","name":"sora-2-pro","display_name":"sora-2-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"description":"OpenAI video model Sora2-pro official API.","typeHints":["video"],"source":"public-provider-conf"},"vision":false},{"id":"doubao-seedream-4-5","name":"doubao-seedream-4-5","display_name":"doubao-seedream-4-5","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedream 4.5 is ByteDance's latest multimodal image model, integrating capabilities such as text-to-image, image-to-image, and multi-image output, along with incorporating common sense and reasoning abilities. Compared to the previous 4.0 model, it significantly improves generation quality, offering better editing consistency and multi-image fusion effects, with more precise control over image details. The generation of small text and small faces is more natural.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"gpt-4o-mini-audio-preview","name":"gpt-4o-mini-audio-preview","display_name":"gpt-4o-mini-audio-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","audio"]},"cost":{"input":0.15,"output":0.6},"limit":{"context":128000,"output":128000},"metadata":{"typeHints":["llm"],"inputModalities":["text","audio"],"pricing":{"input":0.15,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"wan2.6-i2v","name":"wan2.6-i2v","display_name":"wan2.6-i2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wan 2.6 - Text-to-Video generation features intelligent storyboard scheduling supporting multi-shot narration, higher quality sound generation, stable multi-person dialogue, more natural and realistic voice tones, and supports video generation up to 15 seconds in length.","typeHints":["video"],"inputModalities":["image","text"],"source":"public-provider-conf"},"vision":true},{"id":"wan2.6-t2v","name":"wan2.6-t2v","display_name":"wan2.6-t2v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wan 2.6 - Text-to-Video generation features intelligent storyboard scheduling supporting multi-shot narration, higher quality sound generation, stable multi-person dialogue, more natural and realistic voice tones, and supports video generation up to 15 seconds in length.","typeHints":["video"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"cc-glm-4.7","name":"cc-glm-4.7","display_name":"cc-glm-4.7","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.06,"output":0.22},"limit":{"context":8192,"output":8192},"metadata":{"description":"Supports Claude native interface, can be directly requested in Claude Code.","typeHints":["llm"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false},{"id":"cc-minimax-m2.1","name":"cc-minimax-m2.1","display_name":"cc-minimax-m2.1","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":204800,"output":204800},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"coding-glm-4.7","name":"coding-glm-4.7","display_name":"coding-glm-4.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22,"cache_read":0.010998},"limit":{"context":200000,"output":200000},"metadata":{"description":"Only supports OpenAI-compatible formats.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.010998,"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2.1","name":"coding-minimax-m2.1","display_name":"coding-minimax-m2.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":204800,"output":204800},"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2.1-free","name":"coding-minimax-m2.1-free","display_name":"coding-minimax-m2.1-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":204800,"output":204800},"metadata":{"description":"coding-minimax-m2.1-free is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute, 500 total requests per day, and a daily quota of 1 million tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax-m2.1","name":"minimax-m2.1","display_name":"minimax-m2.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.288,"output":1.152},"limit":{"context":204800,"output":204800},"metadata":{"description":"MiniMax-M2.1 redefines efficiency for intelligent agents. It is a compact, fast, and cost-effective MoE model with a total of 230 billion parameters and 10 billion active parameters, designed for top performance in coding and intelligent agent tasks while maintaining strong general intelligence. With only 10 billion active parameters, MiniMax-M2 delivers the complex end-to-end tool usage performance expected from today's leading models, but in a more streamlined form factor, making deployment and scaling easier than ever before.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.288,"output":1.152},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"o3","name":"o3","display_name":"o3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2,"output":8,"cache_read":0.5},"limit":{"context":200000,"output":200000},"metadata":{"description":"OpenAI o3 is a powerful model across multiple domains, setting a new standard for coding, math, science, and visual reasoning tasks.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"input":2,"output":8},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"kimi-for-coding-free","name":"kimi-for-coding-free","display_name":"kimi-for-coding-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0,"output":0},"limit":{"context":256000,"output":256000},"metadata":{"description":"kimi-for-coding-free is a free and open version offered by AIHubMix specifically for Kimi users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute 500 total requests per day, and a daily quota of 1 million tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"o3-pro","name":"o3-pro","display_name":"o3-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":20,"output":80,"cache_read":20},"limit":{"context":200000,"output":200000},"metadata":{"description":"o3-pro\nThis model only supports Requests API interface requests.The model's thinking time is relatively long, so the response will be slow.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":20,"input":20,"output":80},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qianfan-ocr","name":"qianfan-ocr","display_name":"qianfan-ocr","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.062,"output":0.248},"limit":{"context":32000,"output":32000},"metadata":{"description":"Qianfan-OCR-Fast is a multimodal large model specialized for OCR, trained primarily on OCR-domain data while retaining appropriate general multimodal capabilities, and it outperforms Qianfan-OCR.","typeHints":["ocr"],"inputModalities":["text","image"],"pricing":{"input":0.062,"output":0.248},"source":"public-provider-conf"},"vision":true},{"id":"qianfan-ocr-fast","name":"qianfan-ocr-fast","display_name":"qianfan-ocr-fast","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.664,"output":2.738336},"limit":{"context":32000,"output":32000},"metadata":{"description":"Qianfan-OCR-Fast is a multimodal large model specialized for OCR, trained primarily on OCR-domain data while retaining appropriate general multimodal capabilities, and it outperforms Qianfan-OCR.","typeHints":["ocr"],"inputModalities":["text","image"],"pricing":{"input":0.664,"output":2.738336},"source":"public-provider-conf"},"vision":true},{"id":"step-3.5-flash","name":"step-3.5-flash","display_name":"step-3.5-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.11,"output":0.33},"limit":{"context":256000,"output":256000},"metadata":{"description":"step-3.5-flash is stepfun's flagship inference model, designed for high-complexity tasks that require deep reasoning and fast execution. It excels at decomposing multi-step problems, performing tool calls, and maintaining consistency across massive datasets. It is the preferred choice for complex workloads such as long-context agents, advanced software engineering, and end-to-end research automation.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.11,"output":0.33},"source":"public-provider-conf"},"vision":false},{"id":"wan2.2-i2v-plus","name":"wan2.2-i2v-plus","display_name":"wan2.2-i2v-plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"The newly upgraded Tongyi Wanxiang 2.2 text-to-video offers higher video quality. It optimizes video generation stability and success rate, features stronger instruction-following capabilities, consistently maintains image text, portrait, and product consistency, and provides precise camera motion control.","typeHints":["video"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"wan2.5-i2v-preview","name":"wan2.5-i2v-preview","display_name":"wan2.5-i2v-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Tongyi Wanxiang 2.5 - Text-to-Video Preview features a newly upgraded technical architecture, supporting sound generation synchronized with visuals, 10-second long video generation, stronger instruction-following capabilities, and further improvements in motion ability and visual quality.","typeHints":["video"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"wan2.5-t2v-preview","name":"wan2.5-t2v-preview","display_name":"wan2.5-t2v-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Tongyi Wanxiang 2.5 - Text-to-Video Preview, newly upgraded model architecture, supports sound generation synchronized with visuals, supports 10-second long video generation, enhanced instruction compliance, improved motion capability, and further enhanced visual quality.","typeHints":["video"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"flux-2-flex","name":"flux-2-flex","display_name":"flux-2-flex","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"FLUX.2 is purpose-built for real-world creative production workflows. It delivers high-quality images while maintaining character and style consistency across multiple reference images, shows exceptional understanding and execution of structured prompts, and supports complex text reading and writing. It also adheres to brand guidelines, handles lighting, layout, and logo elements with stability, and enables image editing at resolutions up to 4MP — all while preserving fine details, striking a balance between creativity and professional-grade visual output.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"flux-2-pro","name":"flux-2-pro","display_name":"flux-2-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"FLUX.2 is purpose-built for real-world creative production workflows. It delivers high-quality images while maintaining character and style consistency across multiple reference images, shows exceptional understanding and execution of structured prompts, and supports complex text reading and writing. It also adheres to brand guidelines, handles lighting, layout, and logo elements with stability, and enables image editing at resolutions up to 4MP — all while preserving fine details, striking a balance between creativity and professional-grade visual output.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"gemini-2.5-pro","name":"gemini-2.5-pro","display_name":"gemini-2.5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 2.5 Pro is an advanced reasoning model developed by Google, optimized for solving highly complex problems across multiple domains. It can deeply understand large-scale information from diverse sources, including text, audio, images, video, and even entire codebases. The model demonstrates strong reasoning capabilities in coding, mathematics, and STEM-related tasks, and supports long-context analysis for large datasets, codebases, and technical documentation.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context","web","thinking","deepsearch"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-4.6","name":"glm-4.6","display_name":"glm-4.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.273974,"output":1.095896,"cache_read":0.054795},"limit":{"context":200000,"output":200000},"metadata":{"description":"GLM-4.6 is Zhipu’s latest flagship model (total parameters 355B, activation parameters 32B), comprehensively surpassing GLM-4.5. Its coding capability is aligned with Claude Sonnet 4, making it a top domestic coding model; the context window has been expanded from 128K to 200K, better suited for long code and agent tasks; inference capabilities have been significantly enhanced and support tool invocation during processing; improvements have been made in tool calling, search agents, writing style, role play, and multilingual translation. The model is named glm-4.6 and is provided by three vendors, with calls prioritized to the Sophnet platform.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.054795,"input":0.273974,"output":1.095896,"tiers":[{"cache_read":0.109589,"input":0.547946,"output":2.191784,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"glm-4.6v","name":"glm-4.6v","display_name":"glm-4.6v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.137,"output":0.411,"cache_read":0.0274},"limit":{"context":131072,"output":131072},"metadata":{"description":"Zhipu's latest visual reasoning model achieves state-of-the-art visual understanding accuracy at the same scale upon release. It natively supports tool invocation, can automatically complete tasks, supports ultra-long 128K context length, and allows flexible toggling of reasoning.","typeHints":["llm"],"inputModalities":["text","image","video","document"],"pricing":{"cache_read":0.0274,"input":0.137,"output":0.411,"tiers":[{"cache_read":0.0548,"input":0.274,"output":0.822,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"glm-ocr","name":"glm-ocr","display_name":"glm-ocr","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image"]},"cost":{"input":0.0282,"output":0.0282},"limit":{"context":32000,"output":32000},"metadata":{"description":"GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, yet multiple capabilities have reached SOTA levels, establishing a new benchmark for document parsing with a \"small size, high precision\" approach.","typeHints":["ocr"],"inputModalities":["image"],"pricing":{"input":0.0282,"output":0.0282},"source":"public-provider-conf"},"vision":true},{"id":"cc-glm-4.6","name":"cc-glm-4.6","display_name":"cc-glm-4.6","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.06,"output":0.22},"limit":{"context":8192,"output":8192},"metadata":{"description":"for claude code","typeHints":["llm"],"pricing":{"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false},{"id":"coding-glm-4.6","name":"coding-glm-4.6","display_name":"coding-glm-4.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.22,"cache_read":0.010998},"limit":{"context":200000,"output":200000},"metadata":{"typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.010998,"input":0.06,"output":0.22},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-glm-4.6-free","name":"coding-glm-4.6-free","display_name":"coding-glm-4.6-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":200000,"output":200000},"metadata":{"description":"coding-glm-4.6-free is the open and free version of coding-glm-4.6. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 500 requests per day, and a daily token allowance of 1 million.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2","name":"coding-minimax-m2","display_name":"coding-minimax-m2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":204800,"output":204800},"metadata":{"description":"coding-minimax-m2 is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 10 requests per minute, 1,000 total requests per day, and a daily quota of 5 million tokens.204800","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"coding-minimax-m2-free","name":"coding-minimax-m2-free","display_name":"coding-minimax-m2-free","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":204800,"output":204800},"metadata":{"description":"coding-minimax-m2-free is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 5 requests per minute, 500 total requests per day, and a daily quota of 1 million tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-pro-search","name":"gemini-2.5-pro-search","display_name":"gemini-2.5-pro-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-2.5-pro-search integrates Google's official search functionality; the search feature will have an additional separate fee log directly incorporated into the scoring, with detailed logs not displayed; this will be fixed and displayed later; only supports OpenAI-compatible formats for invocation, does not support Gemini SDK; for Gemini's native SDK, please set parameters directly using the official search parameters.","typeHints":["llm","search"],"features":["thinking","web","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"kimi-k2-thinking","name":"kimi-k2-thinking","display_name":"kimi-k2-thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.548,"output":2.192,"cache_read":0.137},"limit":{"context":262144,"output":262144},"metadata":{"description":"Kimi K2 Thinking is Moonshot AI's most advanced open-source inference model to date, extending the K2 series into intelligent agent and long-context inference domains. The model is built on the trillion-parameter mixture of experts (MoE) architecture introduced by Kimi K2, activating 32 billion parameters per forward pass and supporting a context window of 256,000 tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.137,"input":0.548,"output":2.192},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-2.5-flash","name":"gemini-2.5-flash","display_name":"gemini-2.5-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.3,"output":2.499,"cache_read":0.03},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 2.5 Flash is Google’s best model in terms of both performance and cost efficiency, offering a comprehensive set of capabilities. It is the first Flash model to support visible reasoning, allowing insight into the thought process behind its responses. With its strong price–performance ratio, the model is well suited for large-scale processing, low-latency, high-throughput tasks that require reasoning, as well as agent-based application scenarios.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-preview-09-2025","name":"gemini-2.5-flash-preview-09-2025","display_name":"gemini-2.5-flash-preview-09-2025","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.3,"output":2.499,"cache_read":0.03},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"This latest 2.5 Flash model comes with improvements in two key areas we heard consistent feedback on:\n\nBetter agentic tool use: We've improved how the model uses tools, leading to better performance in more complex, agentic and multi-step applications. This model shows noticeable improvements on key agentic benchmarks, including a 5% gain on SWE-Bench Verified, compared to our last release (48.9% → 54%). More efficient: With thinking on, the model is now significantly more cost-efficient—achieving higher quality outputs while using fewer tokens, reducing latency and cost (see charts above).","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"glm-4.5v","name":"glm-4.5v","display_name":"glm-4.5v","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","document"]},"cost":{"input":0.274,"output":0.822},"limit":{"context":65536,"output":65536},"metadata":{"description":"GLM-4.5V is a vision-language foundational model designed for multimodal agent applications. Based on a mixture-of-experts (MoE) architecture, it has 106 billion parameters and 12 billion active parameters. It delivers outstanding performance in video understanding, image question answering, OCR, and document parsing, and achieves significant improvements in front-end web encoding, basic reasoning, and spatial reasoning.","typeHints":["llm","ocr"],"inputModalities":["text","image","video","document"],"pricing":{"input":0.274,"output":0.822,"tiers":[{"input":0.548,"output":1.644,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"gemini-2.5-flash-lite","name":"gemini-2.5-flash-lite","display_name":"gemini-2.5-flash-lite","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 2.5 Flash-Lite is a balanced model from Google, optimized for applications that require low-latency performance. It retains the practical capabilities of the Gemini 2.5 family, including configurable reasoning based on budget, integration with tools such as grounding via Google Search and code execution, multimodal input support, and an ultra-long context window of up to 1 million tokens, delivering a strong balance between efficiency, functionality, and cost.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.01,"input":0.1,"output":0.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-lite-nothink","name":"gemini-2.5-flash-lite-nothink","display_name":"gemini-2.5-flash-lite-nothink","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini 2.5 Flash-Lite is a balanced model from Google, optimized for applications that require low-latency performance. It retains the practical capabilities of the Gemini 2.5 family, including configurable reasoning based on budget, integration with tools such as grounding via Google Search and code execution, multimodal input support, and an ultra-long context window of up to 1 million tokens, delivering a strong balance between efficiency, functionality, and cost.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.01,"input":0.1,"output":0.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-lite-preview-09-2025","name":"gemini-2.5-flash-lite-preview-09-2025","display_name":"gemini-2.5-flash-lite-preview-09-2025","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-2.5-flash-lite latest preview version","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.01,"input":0.1,"output":0.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-lite-preview-09-2025-nothink","name":"gemini-2.5-flash-lite-preview-09-2025-nothink","display_name":"gemini-2.5-flash-lite-preview-09-2025-nothink","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-2.5-flash-lite latest preview version","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.01,"input":0.1,"output":0.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-nothink","name":"gemini-2.5-flash-nothink","display_name":"gemini-2.5-flash-nothink","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.3,"output":2.499,"cache_read":0.03},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini-2.5-flash defaults to thinking enabled; to disable thinking, request the name gemini-2.5-flash-nothink, which only supports OpenAI-compatible format calls and does not support Gemini SDK; for the native Gemini SDK, please set the parameter budget=0 directly.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-search","name":"gemini-2.5-flash-search","display_name":"gemini-2.5-flash-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":0.3,"output":2.499,"cache_read":0.03},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-2.5-flash-search integrates Google's official search functionality; the search feature will have an additional separate fee log directly incorporated into the scoring, with detailed logs not displayed; this will be fixed and displayed later; only supports OpenAI-compatible formats for invocation, does not support Gemini SDK; for Gemini's native SDK, please set parameters directly using the official search parameters.","typeHints":["llm","search"],"features":["web","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-preview-05-20-nothink","name":"gemini-2.5-flash-preview-05-20-nothink","display_name":"gemini-2.5-flash-preview-05-20-nothink","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.3,"output":2.499,"cache_read":0.03},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini-2.5-flash-preview-05-20 is enabled by default for thinking; to disable it, request the name gemini-2.5-flash-preview-05-20-nothink.Only OpenAI-compatible format calls are supported; Gemini SDK is not supported. For the native Gemini SDK, please set the parameter budget=0 directly.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-preview-05-20-search","name":"gemini-2.5-flash-preview-05-20-search","display_name":"gemini-2.5-flash-preview-05-20-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"]},"cost":{"input":0.3,"output":2.499,"cache_read":0.03},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Gemini-2.5 Flash Preview 05-20 Search integrates Google's official search functionality; the search feature will have an additional separate fee log directly integrated into the scoring deduction, with detailed logs not displayed. It will be fixed and displayed later. Only OpenAI-compatible formats are supported for invocation; Gemini SDK is not supported. For Gemini's native SDK, please set parameters directly using the official search parameters.","typeHints":["llm","search"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","video","audio"],"pricing":{"cache_read":0.03,"input":0.3,"output":2.499},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"imagen-4.0-fast-generate-001","name":"imagen-4.0-fast-generate-001","display_name":"imagen-4.0-fast-generate-001","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Imagen 4 is a new-generation image generation model designed to balance high-quality output, inference efficiency, and content safety. It supports image generation, digital watermarking with authenticity verification, user-configurable safety settings, and prompt enhancement via the Prompt Rewriter, while also delivering reliable person generation capabilities. The model ID is imagen-4.0-generate-001, making it suitable for professional creation, design workflows, and various generative AI applications.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"imagen-4.0-generate-001","name":"imagen-4.0-generate-001","display_name":"imagen-4.0-generate-001","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Imagen 4 is a new-generation image generation model designed to balance high-quality output, inference efficiency, and content safety. It supports image generation, digital watermarking with authenticity verification, user-configurable safety settings, and prompt enhancement via the Prompt Rewriter, while also delivering reliable person generation capabilities. The model ID is imagen-4.0-generate-001, making it suitable for professional creation, design workflows, and various generative AI applications.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"imagen-4.0-ultra-generate-001","name":"imagen-4.0-ultra-generate-001","display_name":"imagen-4.0-ultra-generate-001","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-1","name":"gpt-image-1","display_name":"gpt-image-1","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":40},"limit":{"context":8192,"output":8192},"metadata":{"description":"Azure OpenAI’s gpt-image-1 image generation API offers both text-to-image generation and image-to-image editing with text guidance capabilities.\nBefore using this API, please ensure you have the latest OpenAI package installed by running pip install -U openai.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":5,"output":40},"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-1-mini","name":"gpt-image-1-mini","display_name":"gpt-image-1-mini","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":40},"limit":{"context":8192,"output":8192},"metadata":{"description":"OpenAI image generation model gpt-image-1-mini\nBefore use, please run pip install -U openai to upgrade to the latest openai package.","typeHints":["image_generation"],"inputModalities":["text","image"],"pricing":{"input":5,"output":40},"source":"public-provider-conf"},"vision":true},{"id":"o4-mini","name":"o4-mini","display_name":"o4-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"limit":{"context":200000,"output":200000},"metadata":{"description":"o4-mini is a remarkably smart model for its speed and cost-efficiency. This allows it to support significantly higher usage limits than o3, making it a strong high-volume, high-throughput option for everyone with questions that benefit from reasoning.","typeHints":["llm"],"features":["thinking","tool","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.275,"input":1.1,"output":4.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"grok-4","name":"grok-4","display_name":"grok-4","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":3.3,"output":16.5,"cache_read":0.825},"limit":{"context":256000,"output":256000},"metadata":{"description":"Grok, their latest and greatest flagship model, offers unparalleled performance in natural language, math, and reasoning – the perfect jack of all trades.\nThe current pointing model version is grok-4-0709.","typeHints":["llm"],"features":["function_calling","structured_outputs","thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.825,"input":3.3,"output":16.5},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4-fast-non-reasoning","name":"grok-4-fast-non-reasoning","display_name":"grok-4-fast-non-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok-4-fast is a cost-effective inference model developed by xAI that delivers cutting-edge performance with excellent token efficiency. The model features a 2 million token context window, advanced Web and X search capabilities, and a unified architecture supporting both \"inference\" and \"non-inference\" modes. Compared to Grok 4, it reduces thinking tokens by an average of 40% and lowers the price by 98% while achieving the same performance.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.05,"input":0.2,"output":0.5,"tiers":[{"cache_read":0.05,"input":0.4,"output":1,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true},{"id":"grok-4-fast-reasoning","name":"grok-4-fast-reasoning","display_name":"grok-4-fast-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Grok-4-fast is a cost-effective inference model developed by xAI that delivers cutting-edge performance with excellent token efficiency. The model features a 2 million token context window, advanced Web and X search capabilities, and a unified architecture supporting both \"inference\" and \"non-inference\" modes. Compared to Grok 4, it reduces thinking tokens by an average of 40% and lowers the price by 98% while achieving the same performance.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.05,"input":0.2,"output":0.5,"tiers":[{"cache_read":0.05,"input":0.4,"output":1,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kimi-k2-0711","name":"kimi-k2-0711","display_name":"kimi-k2-0711","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.54,"output":2.16},"limit":{"context":131072,"output":131072},"metadata":{"description":"Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent capabilities, featuring a total of 1 trillion parameters and activating 32 billion parameters. In benchmark performance tests across major categories such as general knowledge reasoning, programming, mathematics, and agents, the K2 model outperforms other mainstream open-source models.\nThe Kimi-K2 model supports a context length of 128k tokens.\nIt does not support visual capabilities.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.54,"output":2.16},"source":"public-provider-conf"},"vision":false},{"id":"kimi-k2-instruct","name":"kimi-k2-instruct","display_name":"kimi-k2-instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.54,"output":2.16},"limit":{"context":8192,"output":8192},"metadata":{"description":"Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent capabilities, featuring a total of 1 trillion parameters and activating 32 billion parameters. In benchmark performance tests across major categories such as general knowledge reasoning, programming, mathematics, and agents, the K2 model outperforms other mainstream open-source models.\nThe Kimi-K2 model supports a context length of 128k tokens.\nIt does not support visual capabilities.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.54,"output":2.16},"source":"public-provider-conf"},"vision":false},{"id":"kimi-k2-turbo-preview","name":"kimi-k2-turbo-preview","display_name":"kimi-k2-turbo-preview","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.2,"output":4.8,"cache_read":0.3},"limit":{"context":262144,"output":262144},"metadata":{"description":"The kimi-k2-turbo-preview model is a high-speed version of kimi-k2, with the same model parameters as kimi-k2, but the output speed has been increased from 10 tokens per second to 40 tokens per second.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.3,"input":1.2,"output":4.8},"source":"public-provider-conf"},"vision":false},{"id":"paddleocr-vl-0.9b","name":"paddleocr-vl-0.9b","display_name":"paddleocr-vl-0.9b","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"description":"PaddleOCR-VL is an advanced and efficient document parsing model specifically designed for element recognition within documents. Its core component, PaddleOCR-VL-0.9B, is a compact yet powerful vision-language model (VLM) composed of a NaViT-style dynamic resolution visual encoder and the ERNIE-4.5-0.3B language model, enabling precise element recognition. This model supports 109 languages and excels at recognizing complex elements such as text, tables, formulas, and charts while maintaining extremely low resource consumption. Through comprehensive evaluations on widely used public benchmarks and internal benchmarks, PaddleOCR-VL achieves state-of-the-art (SOTA) performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions, multimodal document parsing approaches, and advanced general-purpose multimodal large models, while also offering faster inference speed.","typeHints":["ocr"],"source":"public-provider-conf"},"vision":false},{"id":"pp-structurev3","name":"pp-structurev3","display_name":"pp-structurev3","type":"chat","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"description":"PP-StructureV3 is an efficient and comprehensive document parsing solution that can effectively convert document images and PDF files into structured content (such as Markdown format). It features powerful capabilities including layout area detection, table recognition, formula recognition, chart understanding, and multi-column reading order recovery. This tool performs excellently across various document types and can handle complex document data.","typeHints":["ocr"],"source":"public-provider-conf"},"vision":false},{"id":"DeepSeek-OCR","name":"DeepSeek-OCR","display_name":"DeepSeek-OCR","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"description":"DeepSeek-OCR is a vision-language model launched by DeepSeek AI, focusing on optical character recognition (OCR) and “contextual optical compression.” The model is designed to explore the limits of compressing contextual information from images, efficiently processing documents and converting them into structured text formats such as Markdown. The model requires an image as input.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":true},{"id":"alicloud-kimi-k2-instruct","name":"alicloud-kimi-k2-instruct","display_name":"alicloud-kimi-k2-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.548,"output":2.192},"limit":{"context":8192,"output":8192},"metadata":{"description":"Kimi-K2 is a MoE architecture foundational model with extremely powerful coding and agent capabilities, featuring a total of 1 trillion parameters and activating 32 billion parameters. In benchmark performance tests across major categories such as general knowledge reasoning, programming, mathematics, and agents, the K2 model outperforms other mainstream open-source models.\nThe Kimi-K2 model supports a context length of 128k tokens.\nIt does not support visual capabilities.","typeHints":["llm"],"pricing":{"input":0.548,"output":2.192},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-vl-235b-a22b-instruct","name":"qwen3-vl-235b-a22b-instruct","display_name":"qwen3-vl-235b-a22b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.274,"output":1.096},"limit":{"context":131072,"output":131072},"metadata":{"description":"The Qwen3 series open-source models include hybrid models, thinking models, and non-thinking models, with both reasoning capabilities and general abilities reaching industry SOTA levels at the same scale.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.274,"output":1.096},"source":"public-provider-conf"},"vision":true},{"id":"qwen3-vl-235b-a22b-thinking","name":"qwen3-vl-235b-a22b-thinking","display_name":"qwen3-vl-235b-a22b-thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.274,"output":2.74},"limit":{"context":131072,"output":131072},"metadata":{"description":"The Qwen3 series open-source models include hybrid models, thinking models, and non-thinking models, with both reasoning capabilities and general abilities reaching industry SOTA levels at the same scale.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.274,"output":2.74},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-vl-30b-a3b-instruct","name":"qwen3-vl-30b-a3b-instruct","display_name":"qwen3-vl-30b-a3b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.1028,"output":0.4112},"limit":{"context":131072,"output":131072},"metadata":{"description":"The Qwen3-VL series’ second-largest MoE model Instruct version offers fast response speed and supports ultra-long contexts such as long videos and long documents; it features comprehensive upgrades in image/video understanding, spatial perception, and universal recognition abilities; it also provides visual 2DD/3D localization capabilities, making it capable of handling complex real-world tasks.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.1028,"output":0.4112},"source":"public-provider-conf"},"vision":true},{"id":"qwen3-vl-30b-a3b-thinking","name":"qwen3-vl-30b-a3b-thinking","display_name":"qwen3-vl-30b-a3b-thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.1028,"output":1.028},"limit":{"context":131072,"output":131072},"metadata":{"description":"The Qwen3-VL series’ second-largest MoE model Thinking version offers fast response speed, stronger multimodal understanding and reasoning, visual agent capabilities, and ultra-long context support for long videos and long documents; it features comprehensive upgrades in image/video understanding, spatial perception, and universal recognition abilities, making it capable of handling complex real-world tasks.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.1028,"output":1.028},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"veo-3.0-generate-preview","name":"veo-3.0-generate-preview","display_name":"veo-3.0-generate-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Veo 3.0 Generate Preview is an advanced AI video generation model that supports text-to-video creation with synchronized audio, featuring excellent physical simulation and lip-sync capabilities. Users can generate vivid video clips from short story prompts. 🎟️ Limited-Time Deal: Save 10% Now.","typeHints":["video"],"inputModalities":["text","image","video"],"source":"public-provider-conf"},"vision":true},{"id":"veo-3.1-fast-generate-preview","name":"veo-3.1-fast-generate-preview","display_name":"veo-3.1-fast-generate-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Veo 3.1 is Google's state-of-the-art model for generating high-fidelity, 8-second 720p , 1080p or 4k videos featuring stunning realism and natively generated audio.","typeHints":["video"],"inputModalities":["text","image","video"],"source":"public-provider-conf"},"vision":true},{"id":"veo-3.1-generate-preview","name":"veo-3.1-generate-preview","display_name":"veo-3.1-generate-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Veo 3.1 is Google's state-of-the-art model for generating high-fidelity, 8-second 720p , 1080p or 4k videos featuring stunning realism and natively generated audio.","typeHints":["video"],"inputModalities":["text","image","video"],"source":"public-provider-conf"},"vision":true},{"id":"deepseek-ocr","name":"deepseek-ocr","display_name":"deepseek-ocr","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.02,"output":0.02},"limit":{"context":8000,"output":8000},"metadata":{"description":"DeepSeek-OCR is a vision-language model launched by DeepSeek AI, focusing on optical character recognition (OCR) and “contextual optical compression.” The model is designed to explore the limits of compressing contextual information from images, efficiently processing documents and converting them into structured text formats such as Markdown. The model requires an image as input.","typeHints":["ocr"],"inputModalities":["text","image"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":true},{"id":"ernie-5.0-thinking-exp","name":"ernie-5.0-thinking-exp","display_name":"ernie-5.0-thinking-exp","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.82192,"output":3.28768,"cache_read":0.82192},"limit":{"context":119000,"output":119000},"metadata":{"description":"ERNIE 5.0 is the next-generation natively multimodal foundation model in the ERNIE family. Built on a unified multimodal architecture, it jointly learns from text, images, audio, and video to deliver broad multimodal capabilities.\n\nERNIE 5.0 features significantly upgraded core capabilities and shows strong performance across benchmarks, with notable gains in multimodal understanding, instruction following, creative writing, factual accuracy, and agent planning with tool use.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text"],"pricing":{"cache_read":0.82192,"input":0.82192,"output":3.28768,"tiers":[{"cache_read":1.36986,"input":1.36986,"output":5.47944,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"flux-kontext-max","name":"flux-kontext-max","display_name":"flux-kontext-max","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation"],"source":"public-provider-conf"},"vision":false},{"id":"gemini-2.5-flash-image-preview","name":"gemini-2.5-flash-image-preview","display_name":"gemini-2.5-flash-image-preview","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"]},"cost":{"input":0.3,"output":1.2},"limit":{"context":32800,"output":32800},"metadata":{"description":"Aihubmix supports the gemini-2.5-flash-image-preview model; you can add extra parameters modalities=[\"text\", \"image\"] through the OpenAI-compatible chat interface; https://docs.aihubmix.com/en/api/Gemini-Guides#gemini-2-5-flash%3A-quick-task-support","typeHints":["image_generation"],"inputModalities":["image","text"],"pricing":{"input":0.3,"output":1.2},"source":"public-provider-conf"},"vision":true},{"id":"glm-4.5","name":"glm-4.5","display_name":"glm-4.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.4,"output":1.6},"limit":{"context":131072,"output":131072},"metadata":{"description":"GLM-4.5","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.4,"output":1.6},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4.1","name":"gpt-4.1","display_name":"gpt-4.1","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2,"output":8,"cache_read":0.5},"limit":{"context":1047576,"output":1047576},"metadata":{"description":"The latest flagship multimodal model supports million-token context, with encoding capability (SWE-bench 54.6%) and instruction-following (Scale AI 38.3%) performance significantly surpassing GPT-4o, while reducing costs by 26%, making it suitable for complex tasks. Its automatic caching mechanism offers a 75% cost reduction on cache hits.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.5,"input":2,"output":8},"source":"public-provider-conf"},"vision":true},{"id":"gpt-4.1-mini","name":"gpt-4.1-mini","display_name":"gpt-4.1-mini","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"limit":{"context":1047576,"output":1047576},"metadata":{"description":"Lightweight, high-performance model with million-token context and near-flagship-level encoding and image understanding capabilities, while reducing costs by 83%. It is suitable for rapid development and small to medium-sized applications. The automatic caching mechanism provides a 75% cost reduction on cache hits.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.1,"input":0.4,"output":1.6},"source":"public-provider-conf"},"vision":true},{"id":"aihubmix-router","name":"aihubmix-router","display_name":"aihubmix-router","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"limit":{"context":8192,"output":8192},"metadata":{"description":"New model routing capability; request aihubmix-router to automatically route models based on question complexity, so everyone no longer needs to manually switch models; in our tests comparing the use of the model router versus only using GPT-4.1, we observed up to 60% cost savings while maintaining similar accuracy.  \nThe context length of the model router depends on the base model used for each prompt. Input size is 200,000, output size is 32,768.  \nCurrently, there are four routing models: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o4-mini.  \nPricing: Due to our current billing structure system, requests through aihubmix-router are billed at the price of gpt-4.1-mini regardless of which final model is used; future billing will be based on the actual model invoked.  \nEveryone is welcome to try it out; the interface will return the name of the actual called model.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.1,"input":0.4,"output":1.6},"source":"public-provider-conf"},"vision":true},{"id":"gpt-4.1-nano","name":"gpt-4.1-nano","display_name":"gpt-4.1-nano","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"limit":{"context":1047576,"output":1047576},"metadata":{"description":"Ultra-lightweight model with million-token context, optimized for speed and low latency, costing only $0.10 per million input tokens. It is suitable for edge computing and real-time interaction. The automatic caching mechanism offers a 75% cost reduction on cache hits.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":0.025,"input":0.1,"output":0.4},"source":"public-provider-conf"},"vision":true},{"id":"gemini-2.5-pro-preview-05-06","name":"gemini-2.5-pro-preview-05-06","display_name":"gemini-2.5-pro-preview-05-06","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image","video","audio","pdf"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"gemini-2.5-pro latest model","typeHints":["llm"],"features":["thinking","long_context"],"inputModalities":["text","image","video","audio","pdf"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro-preview-03-25","name":"gemini-2.5-pro-preview-03-25","display_name":"gemini-2.5-pro-preview-03-25","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":8192,"output":8192},"metadata":{"description":"Supports high concurrency.  \nThe Gemini 2.5 Pro preview version is here, with higher limits for production testing.  \nGoogle's latest and most powerful model;","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro-preview-05-06-search","name":"gemini-2.5-pro-preview-05-06-search","display_name":"gemini-2.5-pro-preview-05-06-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image","audio","video"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":8192,"output":8192},"metadata":{"description":"Integrated with Google's official search function.","typeHints":["llm","search"],"features":["thinking","web"],"inputModalities":["text","image","audio","video"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro-preview-03-25-search","name":"gemini-2.5-pro-preview-03-25-search","display_name":"gemini-2.5-pro-preview-03-25-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","audio","video"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":8192,"output":8192},"metadata":{"description":"Integrated with Google's official search function.","typeHints":["llm","search"],"features":["thinking","web","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","audio","video"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen3-max-preview","name":"qwen3-max-preview","display_name":"qwen3-max-preview","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.846,"output":3.384,"cache_read":0.1692},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen3-Max-Preview is the latest preview model in the Qwen3 series. This version is functionally equivalent to Qwen3-Max-Thinking — simply set extra_body={\"enable_thinking\": True} to enable the thinking mode. Compared to the Qwen2.5 series, it delivers significant improvements in overall general capabilities, including English–Chinese text understanding, complex instruction following, open-ended reasoning, multilingual processing, and tool-use proficiency. The model also exhibits fewer hallucinations and stronger overall reliability.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.1692,"input":0.846,"output":3.384,"tiers":[{"cache_read":0.2816,"input":1.408,"output":5.632,"tier":{"size":32000,"type":"context"}},{"cache_read":0.42256,"input":2.1128,"output":8.4512,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-max","name":"qwen3-max","display_name":"qwen3-max","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.4508,"output":1.8032,"cache_read":0.09016},"limit":{"context":262144,"output":262144},"metadata":{"description":"The Tongyi Qianwen 3 series Max model has undergone special upgrades in intelligent agent programming and tool invocation compared to the preview version. The officially released model this time reaches SOTA level in the field and is adapted to more complex intelligent agent scenarios.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.09016,"cache_write":0.5635,"input":0.4508,"output":1.8032,"tiers":[{"cache_read":0.1804,"cache_write":1.1275,"input":0.902,"output":5.412,"tier":{"size":32000,"type":"context"}},{"cache_read":0.27044,"cache_write":1.69025,"input":1.3522,"output":8.1132,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-next-80b-a3b-instruct","name":"qwen3-next-80b-a3b-instruct","display_name":"qwen3-next-80b-a3b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.138,"output":0.552},"limit":{"context":256000,"output":256000},"metadata":{"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned model in the Qwen3-Next series, optimized for delivering fast, stable, and direct final answers without showing its reasoning steps (\"thinking traces\").\n\nUnlike chain-of-thought models, it focuses on generating consistent, instruction-following outputs, making it ideal for production environments. It excels at complex tasks like reasoning and coding while maintaining high throughput and stability, especially with ultra-long inputs and multi-turn dialogues.\n\nEngineered for efficiency, its performance rivals larger Qwen3 systems, making it perfectly suited for RAG, tool use, and agentic workflows where deterministic results are critical.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.138,"output":0.552},"source":"public-provider-conf"},"vision":true},{"id":"qwen3-next-80b-a3b-thinking","name":"qwen3-next-80b-a3b-thinking","display_name":"qwen3-next-80b-a3b-thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.142,"output":1.42},"limit":{"context":256000,"output":256000},"metadata":{"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that excels by outputting structured 'thinking' traces (Chain-of-Thought) by default.\n\nDesigned for hard, multi-step problems, it is ideal for tasks like math proofs, code synthesis, logic puzzles, and agentic planning. Compared to other Qwen3 variants, it offers greater stability during long reasoning chains and is tuned to follow complex instructions without getting repetitive or off-task.\n\nThis model is perfectly suited for agent frameworks, tool use (function calling), and benchmarks where a step-by-step breakdown is required. It leverages throughput-oriented techniques for fast generation of detailed, procedural outputs.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.142,"output":1.42},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-235b-a22b-instruct-2507","name":"qwen3-235b-a22b-instruct-2507","display_name":"qwen3-235b-a22b-instruct-2507","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.28,"output":1.12},"limit":{"context":262144,"output":262144},"metadata":{"description":"Qwen3-235B-A22B-Instruct-2507","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.28,"output":1.12},"source":"public-provider-conf"},"vision":true},{"id":"qwen3-235b-a22b-thinking-2507","name":"qwen3-235b-a22b-thinking-2507","display_name":"qwen3-235b-a22b-thinking-2507","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.28,"output":2.8},"limit":{"context":262144,"output":262144},"metadata":{"description":"The open-source thinking model based on Qwen3 has significantly improved in logical ability, general capability, knowledge enhancement, and creative ability compared to the previous version (Tongyi Qianwen 3-235B-A22B). It is suitable for high-difficulty and strong reasoning scenarios.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.28,"output":2.8},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-coder-30b-a3b-instruct","name":"qwen3-coder-30b-a3b-instruct","display_name":"qwen3-coder-30b-a3b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.8},"limit":{"context":262144,"output":262144},"metadata":{"description":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, achieving state-of-the-art performance compared to open-source models.The model adopts tiered pricing.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.8,"tiers":[{"input":0.308218,"output":1.232872,"tier":{"size":32000,"type":"context"}},{"input":1.027396,"output":5.13698,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-coder-480b-a35b-instruct","name":"qwen3-coder-480b-a35b-instruct","display_name":"qwen3-coder-480b-a35b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.82,"output":3.28},"limit":{"context":262000,"output":262000},"metadata":{"description":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, achieving state-of-the-art performance compared to open-source models.The model adopts tiered pricing.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.82,"output":3.28,"tiers":[{"input":1.232876,"output":4.931504,"tier":{"size":32000,"type":"context"}},{"input":2.054794,"output":8.219176,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-coder-flash","name":"qwen3-coder-flash","display_name":"qwen3-coder-flash","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.136,"output":0.544},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.136,"output":0.544,"tiers":[{"input":0.205478,"output":0.821912,"tier":{"size":32000,"type":"context"}},{"input":0.342464,"output":1.369856,"tier":{"size":128000,"type":"context"}},{"input":0.68493,"output":3.42465,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-coder-plus","name":"qwen3-coder-plus","display_name":"qwen3-coder-plus","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.54,"output":2.16,"cache_read":0.108},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, excels in tool invocation and environment interaction, and can achieve autonomous programming with outstanding coding abilities while also possessing general capabilities.The model adopts tiered pricing.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.108,"input":0.54,"output":2.16,"tiers":[{"input":0.821916,"output":3.287664,"tier":{"size":32000,"type":"context"}},{"input":1.369862,"output":5.479448,"tier":{"size":128000,"type":"context"}},{"input":2.739726,"output":27.39726,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-coder-plus-2025-07-22","name":"qwen3-coder-plus-2025-07-22","display_name":"qwen3-coder-plus-2025-07-22","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.54,"output":2.16,"cache_read":0.108},"limit":{"context":128000,"output":128000},"metadata":{"description":"The code generation model based on Qwen3 has powerful Coding Agent capabilities, excels in tool invocation and environment interaction, and can achieve autonomous programming with outstanding coding abilities while also possessing general capabilities.The model adopts tiered pricing.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"cache_read":0.108,"input":0.54,"output":2.16,"tiers":[{"input":0.821916,"output":3.287664,"tier":{"size":32000,"type":"context"}},{"input":1.369862,"output":5.479448,"tier":{"size":128000,"type":"context"}},{"input":2.739726,"output":27.39726,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"LongCat-Flash-Chat","name":"LongCat-Flash-Chat","display_name":"LongCat-Flash-Chat","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.14,"output":0.7},"limit":{"context":8192,"output":8192},"metadata":{"description":"Meituan has officially released and open-sourced LongCat-Flash-Chat, which utilizes an innovative Mixture of Experts (MoE) and \"zero-computation expert\" mechanism to achieve a total of 560B parameters, while only activating around 27B parameters per token as needed. At the same time, end-to-end optimization for agents (including a self-built evaluation set and multi-agent trajectory data) significantly enhances its performance in tool usage and complex task orchestration.","typeHints":["llm"],"pricing":{"input":0.14,"output":0.7},"source":"public-provider-conf"},"vision":false},{"id":"jina-embeddings-v5-text-nano","name":"jina-embeddings-v5-text-nano","display_name":"jina-embeddings-v5-text-nano","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"A 3.8-billion-parameter general vector model (embedding model) for state-of-the-art multilingual embeddings for edge deployment.","typeHints":["embedding"],"inputModalities":["text","image"],"pricing":{"input":0.05,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"jina-embeddings-v5-text-small","name":"jina-embeddings-v5-text-small","display_name":"jina-embeddings-v5-text-small","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"A 3.8-billion-parameter general vector (embedding) model providing state-of-the-art multilingual embeddings with task-specific adapters.","typeHints":["embedding"],"inputModalities":["text","image"],"pricing":{"input":0.05,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"gemini-2.5-pro-preview-06-05-search","name":"gemini-2.5-pro-preview-06-05-search","display_name":"gemini-2.5-pro-preview-06-05-search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","audio","video"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":8192,"output":8192},"metadata":{"description":"Integrated with Google's official search function.","typeHints":["llm","search"],"features":["thinking","web","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","audio","video"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"ernie-5.0-thinking-preview","name":"ernie-5.0-thinking-preview","display_name":"ernie-5.0-thinking-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.822,"output":3.288,"cache_read":0.822},"limit":{"context":183000,"output":183000},"metadata":{"description":"The new generation Wenxin model, Wenxin 5.0, is a native full-modal large model that adopts native full-modal unified modeling technology, jointly modeling text, images, audio, and video, possessing comprehensive full-modal capabilities. Wenxin 5.0's basic abilities are comprehensively upgraded, performing excellently on benchmark test sets, especially in multimodal understanding, instruction compliance, creative writing, factual accuracy, intelligent agent planning, and tool application.","typeHints":["llm"],"features":["thinking","structured_outputs","function_calling"],"inputModalities":["text"],"pricing":{"cache_read":0.822,"input":0.822,"output":3.288,"tiers":[{"cache_read":1.36986,"input":1.36986,"output":5.47944,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionAI/Ling-1T","name":"inclusionAI/Ling-1T","display_name":"inclusionAI/Ling-1T","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.548,"output":2.192},"limit":{"context":8192,"output":8192},"metadata":{"description":"Ling-1T is the first flagship non-thinking model in the “Ling 2.0” series, featuring 1 trillion total parameters and approximately 50 billion active parameters per token. Built on the Ling 2.0 architecture, Ling-1T is designed to push the limits of efficient inference and scalable cognition. Ling-1T-base was pretrained on over 20 trillion high-quality, reasoning-intensive tokens, supports up to a 128K context length, and incorporates an Evolutionary Chain of Thought (Evo-CoT) process during mid-stage and post-stage training. This training regimen greatly enhances the model’s efficiency and depth of reasoning, enabling Ling-1T to achieve top performance across multiple complex reasoning benchmarks, balancing accuracy and efficiency.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.548,"output":2.192},"source":"public-provider-conf"},"vision":false},{"id":"inclusionAI/Ring-1T","name":"inclusionAI/Ring-1T","display_name":"inclusionAI/Ring-1T","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.548,"output":2.192},"limit":{"context":8192,"output":8192},"metadata":{"description":"Ring-1T is an open-source idea model with a trillion parameters released by the Bailing team. It is based on the Ling 2.0 architecture and the Ling-1T-base foundational model for training, with a total parameter count of 1 trillion, an active parameter count of 50 billion, and supports up to a 128K context window. The model is trained via large-scale verifiable reward reinforcement learning (RLVR), combined with the self-developed Icepop reinforcement learning stabilization method and the efficient ASystem reinforcement learning system, significantly improving the model’s deep reasoning and natural language reasoning capabilities. Ring-1T achieves leading performance among open-source models on high-difficulty reasoning benchmarks such as mathematics competitions (e.g., IMO 2025), code generation (e.g., ICPC World Finals 2025), and logical reasoning.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.548,"output":2.192},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gte-rerank-v2","name":"gte-rerank-v2","display_name":"gte-rerank-v2","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.11,"output":0.11},"limit":{"context":8192,"output":8192},"metadata":{"description":"gte-rerank-v2 is a multilingual unified text ranking model developed by Tongyi Lab, covering multiple major languages worldwide and providing high-quality text ranking services. It is typically used in scenarios such as semantic retrieval and RAG, and can simply and effectively improve text retrieval performance. Given a query and a set of candidate texts (documents), the model ranks the candidates from highest to lowest based on their semantic relevance to the query.","typeHints":["rerank"],"inputModalities":["text","image"],"pricing":{"input":0.11,"output":0.11},"source":"public-provider-conf"},"vision":true},{"id":"inclusionAI/Ling-flash-2.0","name":"inclusionAI/Ling-flash-2.0","display_name":"inclusionAI/Ling-flash-2.0","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.136,"output":0.544},"limit":{"context":8192,"output":8192},"metadata":{"description":"Ling-flash-2.0 is a language model from inclusionAI with a total of 100 billion parameters, of which 6.1 billion are activated per token (4.8 billion non-embedding). As part of the Ling 2.0 architecture series, it is designed as a lightweight yet powerful Mixture-of-Experts (MoE) model. It aims to deliver performance comparable to or even exceeding that of 40B-level dense models and other larger MoE models, but with a significantly smaller active parameter count. The model represents a strategy focused on achieving high performance and efficiency through extreme architectural design and training methods.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.136,"output":0.544},"source":"public-provider-conf"},"vision":false},{"id":"inclusionAI/Ling-mini-2.0","name":"inclusionAI/Ling-mini-2.0","display_name":"inclusionAI/Ling-mini-2.0","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.068,"output":0.272},"limit":{"context":8192,"output":8192},"metadata":{"description":"Ling-mini-2.0 is a small-sized, high-performance large language model based on the MoE architecture. It has a total of 16 billion parameters, but only activates 1.4 billion parameters per token (non-embedding 789 million), achieving extremely high generation speed. Thanks to the efficient MoE design and large-scale high-quality training data, despite activating only 1.4 billion parameters, Ling-mini-2.0 still demonstrates top-tier performance on downstream tasks comparable to dense LLMs under 10 billion parameters and even larger-scale MoE models.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.068,"output":0.272},"source":"public-provider-conf"},"vision":false},{"id":"inclusionAI/Ring-flash-2.0","name":"inclusionAI/Ring-flash-2.0","display_name":"inclusionAI/Ring-flash-2.0","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.136,"output":0.544},"limit":{"context":8192,"output":8192},"metadata":{"description":"Ring-flash-2.0 is a high-performance thinking model deeply optimized based on the Ling-flash-2.0-base. It uses a mixture-of-experts (MoE) architecture with a total of 100 billion parameters, but only activates 6.1 billion parameters per inference. The model employs the original Icepop algorithm to solve the instability issues of large MoE models during reinforcement learning (RL) training, enabling its complex reasoning capabilities to continuously improve over long training cycles. Ring-flash-2.0 has achieved significant breakthroughs on multiple high-difficulty benchmarks, including mathematics competitions, code generation, and logical reasoning. Its performance not only surpasses top dense models under 40 billion parameters but also rivals larger open-source MoE models and closed-source high-performance thinking models. Although the model focuses on complex reasoning, it also performs exceptionally well on creative writing tasks. Furthermore, thanks to its efficient architecture, Ring-flash-2.0 delivers high performance with low-latency inference, significantly reducing deployment costs in high-concurrency scenarios.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.136,"output":0.544},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"jina-deepsearch-v1","name":"jina-deepsearch-v1","display_name":"jina-deepsearch-v1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"DeepSearch combines search, reading, and reasoning capabilities to pursue the best possible answer. It's fully compatible with OpenAI's Chat API format—just replace api.openai.com with aihubmix.com to get started.  \nThe stream will return the thinking process.","typeHints":["llm","search"],"features":["thinking","web","deepsearch"],"inputModalities":["text","image"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"jina-embeddings-v4","name":"jina-embeddings-v4","display_name":"jina-embeddings-v4","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"A general-purpose vector model with 3.8 billion parameters, used for multimodal and multilingual retrieval, supporting both unidirectional and multi-vector embedding outputs.","typeHints":["embedding"],"inputModalities":["text","image"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":true},{"id":"jina-reranker-v3","name":"jina-reranker-v3","display_name":"jina-reranker-v3","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":131072,"output":131072},"metadata":{"description":"Multimodal multilingual document reranker, 131K context, 0.6B parameters, for visual document sorting.","typeHints":["rerank"],"inputModalities":["text","image"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":true},{"id":"llama-4-maverick","name":"llama-4-maverick","display_name":"llama-4-maverick","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Llama 4 Maverick is a high-capacity Mixture-of-Experts (MoE) model from Meta, featuring 400B total parameters and 128 experts, while activating an efficient 17B parameters per inference. Engineered for peak performance, it excels at advanced multimodal tasks.\n\nMaverick natively supports text and image input, producing multilingual text and code. With a 1-million-token context window and instruction tuning, it is optimized for complex image reasoning and general-purpose assistant-like interactions.\n\nReleased under the Llama 4 Community License, Maverick is ideal for research and commercial applications demanding state-of-the-art multimodal understanding and high throughput.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":true},{"id":"llama-4-scout","name":"llama-4-scout","display_name":"llama-4-scout","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":0.2},"limit":{"context":131072,"output":131072},"metadata":{"description":"Llama 4 Scout is a highly efficient Mixture-of-Experts (MoE) model from Meta, activating 17B out of 109B total parameters per inference. It natively supports multimodal input (text and image) and multilingual output (text and code) across 12 languages.\n\nDesigned for assistant-style interaction and visual reasoning, Scout features a massive 10-million-token context window. It is instruction-tuned for tasks like multilingual chat and image understanding and is released under the Llama 4 Community License for local or commercial deployment.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":true},{"id":"bce-reranker-base","name":"bce-reranker-base","display_name":"bce-reranker-base","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.068,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","typeHints":["rerank"],"inputModalities":["text","image"],"pricing":{"input":0.068,"output":0},"source":"public-provider-conf"},"vision":true},{"id":"codex-mini-latest","name":"codex-mini-latest","display_name":"codex-mini-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.5,"output":6,"cache_read":0.375},"limit":{"context":8192,"output":8192},"metadata":{"description":"Only supports v1/responses API calls.https://docs.aihubmix.com/en/api/Responses-API\ncodex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.375,"input":1.5,"output":6},"source":"public-provider-conf"},"vision":true},{"id":"qwen-image","name":"qwen-image","display_name":"qwen-image","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen-Image is a foundational image generation model in the Qwen series, achieving significant progress in complex text rendering and precise image editing. Experiments show that the model has strong general capabilities in image generation and editing, especially excelling in Chinese text rendering.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"qwen-image-edit","name":"qwen-image-edit","display_name":"qwen-image-edit","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen-Image-Edit is the image editing version of Qwen-Image. Based on the 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image's unique text rendering capabilities to image editing tasks, achieving precise text editing. Additionally, Qwen-Image-Edit can input the same image into Qwen2.5-VL (for visual semantic control) and the VAE encoder (for visual appearance control), enabling both semantic and appearance editing functionalities.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"qwen-image-max","name":"qwen-image-max","display_name":"qwen-image-max","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen-Image-Edit is the image editing version of Qwen-Image. Based on the 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image's unique text rendering capabilities to image editing tasks, achieving precise text editing. Additionally, Qwen-Image-Edit can input the same image into Qwen2.5-VL (for visual semantic control) and the VAE encoder (for visual appearance control), enabling both semantic and appearance editing functionalities.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"qwen-mt-plus","name":"qwen-mt-plus","display_name":"qwen-mt-plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.492,"output":1.476},"limit":{"context":16000,"output":16000},"metadata":{"description":"Based on the comprehensive upgrade of Qwen3, this flagship translation large model supports bidirectional translation across 92 languages. It offers fully enhanced model performance and translation quality, along with more stable terminology customization, format fidelity, and domain-prompting capabilities, making translations more accurate and natural.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.492,"output":1.476},"source":"public-provider-conf"},"vision":false},{"id":"qwen-mt-turbo","name":"qwen-mt-turbo","display_name":"qwen-mt-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.192,"output":0.534912},"limit":{"context":16000,"output":16000},"metadata":{"description":"Based on the comprehensive upgrade of Qwen3, this flagship translation large model supports bidirectional translation across 92 languages. It offers fully enhanced model performance and translation quality, along with more stable terminology customization, format fidelity, and domain-prompting capabilities, making translations more accurate and natural.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.192,"output":0.534912},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-embedding-0.6b","name":"qwen3-embedding-0.6b","display_name":"qwen3-embedding-0.6b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.068,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen3 Embedding model series is the latest proprietary model family from Qwen, specifically designed for text embedding and ranking tasks. Based on the dense base models of the Qwen3 series, it offers comprehensive text embedding and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the excellent multilingual capabilities, long-text understanding, and reasoning skills of its base models. The Qwen3 Embedding series demonstrates significant advancements in various text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bilingual text mining.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.068,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-embedding-4b","name":"qwen3-embedding-4b","display_name":"qwen3-embedding-4b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.068,"output":0.068},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen3 Embedding model series is the latest proprietary model family from Qwen, specifically designed for text embedding and ranking tasks. Based on the dense base models of the Qwen3 series, it offers comprehensive text embedding and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the excellent multilingual capabilities, long-text understanding, and reasoning skills of its base models. The Qwen3 Embedding series demonstrates significant advancements in various text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bilingual text mining.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.068,"output":0.068},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-embedding-8b","name":"qwen3-embedding-8b","display_name":"qwen3-embedding-8b","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.068,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen3 Embedding model series is the latest proprietary model family from Qwen, specifically designed for text embedding and ranking tasks. Based on the dense base models of the Qwen3 series, it offers comprehensive text embedding and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the excellent multilingual capabilities, long-text understanding, and reasoning skills of its base models. The Qwen3 Embedding series demonstrates significant advancements in various text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bilingual text mining.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.068,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-reranker-0.6b","name":"qwen3-reranker-0.6b","display_name":"qwen3-reranker-0.6b","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.11,"output":0.11},"limit":{"context":16000,"output":16000},"metadata":{"description":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","typeHints":["rerank"],"inputModalities":["text","image"],"pricing":{"input":0.11,"output":0.11},"source":"public-provider-conf"},"vision":true},{"id":"qwen3-reranker-4b","name":"qwen3-reranker-4b","display_name":"qwen3-reranker-4b","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.11,"output":0.11},"limit":{"context":8192,"output":8192},"metadata":{"description":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","typeHints":["rerank"],"inputModalities":["text","image"],"pricing":{"input":0.11,"output":0.11},"source":"public-provider-conf"},"vision":true},{"id":"qwen3-reranker-8b","name":"qwen3-reranker-8b","display_name":"qwen3-reranker-8b","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.11,"output":0.11},"limit":{"context":8192,"output":8192},"metadata":{"description":"Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.","typeHints":["rerank"],"inputModalities":["text","image"],"pricing":{"input":0.11,"output":0.11},"source":"public-provider-conf"},"vision":true},{"id":"tao-8k","name":"tao-8k","display_name":"tao-8k","type":"embedding","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.068,"output":0.068},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"pricing":{"input":0.068,"output":0.068},"source":"public-provider-conf"},"vision":false},{"id":"doubao-seedream-4-0","name":"doubao-seedream-4-0","display_name":"doubao-seedream-4-0","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Seedream 4.0 is a SOTA-level multimodal image creation model based on leading architecture. It breaks the creative boundaries of traditional text-to-image models by natively supporting text, single image, and multiple image inputs. Users can freely combine text and images to achieve various creative styles within the same model, such as multi-image fusion creation based on subject consistency, image editing, and set image generation, making image creation more flexible and controllable.\nSeedream 4.0 supports composite editing with up to 10 images in a single input. Through deep reasoning of prompt words, it automatically adapts the optimal image aspect ratio and generation quantity, enabling continuous output of up to 15 content-related images at one time. Additionally, the model significantly improves the accuracy and content diversity of Chinese generation, supports 4K ultra-high-definition output, and provides a one-stop solution from generation to editing for professional image creation.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"embedding-v1","name":"embedding-v1","display_name":"embedding-v1","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.068,"output":0},"limit":{"context":8192,"output":8192},"metadata":{"description":"Embedding-V1 is a text representation model based on Baidu's Wenxin large model technology, capable of converting text into numerical vector forms for applications such as text retrieval, information recommendation, and knowledge mining. Embedding-V1 provides an Embeddings interface that generates corresponding vector representations based on the input content. By calling this interface, you can input text into the model and obtain the corresponding vector representations for subsequent text processing and analysis.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.068,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"ernie-4.5-turbo-latest","name":"ernie-4.5-turbo-latest","display_name":"ernie-4.5-turbo-latest","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.11,"output":0.44},"limit":{"context":135000,"output":135000},"metadata":{"description":"Wenxin 4.5 Turbo also has significant improvements in hallucination reduction, logical reasoning, and coding capabilities. Compared to Wenxin 4.5, it is faster and more affordable.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.11,"output":0.44},"source":"public-provider-conf"},"vision":true},{"id":"glm-4.5-x","name":"glm-4.5-x","display_name":"glm-4.5-x","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":2.2,"output":8.91,"cache_read":0.44},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-4.5-X is the high-speed version of GLM-4.5, offering powerful performance with a generation speed of up to 100 tokens per second.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.44,"input":2.2,"output":8.91},"source":"public-provider-conf"},"vision":false},{"id":"gme-qwen2-vl-2b-instruct","name":"gme-qwen2-vl-2b-instruct","display_name":"gme-qwen2-vl-2b-instruct","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.138,"output":0.138},"limit":{"context":8192,"output":8192},"metadata":{"description":"The GME-Qwen2VL series is a unified multimodal Embedding model trained based on the Qwen2-VL multimodal large language model (MLLMs). The GME model supports three types of inputs: text, images, and image-text pairs. All these input types can generate universal vector representations and exhibit excellent retrieval performance.","typeHints":["embedding"],"inputModalities":["text","image","video"],"pricing":{"input":0.138,"output":0.138},"source":"public-provider-conf"},"vision":true},{"id":"jina-clip-v2","name":"jina-clip-v2","display_name":"jina-clip-v2","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"Multi-modal Embeddings Model, multilingual, 1024-dimensional, 865M parameters.","typeHints":["embedding"],"inputModalities":["text","image"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":true},{"id":"jina-reranker-m0","name":"jina-reranker-m0","display_name":"jina-reranker-m0","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"Multimodal multilingual document reranker, 10K context, 2.4B parameters, for visual document sorting.","typeHints":["rerank"],"inputModalities":["text","image"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":true},{"id":"jina-colbert-v2","name":"jina-colbert-v2","display_name":"jina-colbert-v2","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"Multi-language ColBERT embeddings model, 560M parameters, used for embedding and reranking.","typeHints":["embedding","rerank"],"inputModalities":["text"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4o-search-preview","name":"gpt-4o-search-preview","display_name":"gpt-4o-search-preview","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":128000,"output":128000},"metadata":{"description":"Using the Chat Completions API, you can directly access the fine-tuned models and tool used by Search in ChatGPT.\n\nWhen using Chat Completions, the model always retrieves information from the web before responding to your query. To use web_search_preview as a tool that models like gpt-4o and gpt-4o-mini invoke only when necessary, switch to using the Responses API.\n\nCurrently, you need to use one of these models to use web search in Chat Completions:\n\ngpt-4o-search-preview\ngpt-4o-mini-search-preview\nWeb search parameter example\nimport OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst completion = await client.chat.completions.create({\n    model: \"gpt-4o-search-preview\",\n    web_search_options: {},\n    messages: [{\n        \"role\": \"user\",\n        \"content\": \"What was a positive news story from today?\"\n    }],\n});\n\nconsole.log(completion.choices[0].message.content);\nOutput and citations\nThe API response item in the choices array will include:\n\nmessage.content with the text result from the model, inclusive of any inline citations\nannotations with a list of cited URLs\nBy default, the model's response will include inline citations for URLs found in the web search results. In addition to this, the url_citation annotation object will contain the URL and title of the cited source, as well as the start and end index characters in the model's response where those sources were used.","typeHints":["llm","search"],"features":["web","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":1.25,"input":2.5,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"gpt-4o-mini-search-preview","name":"gpt-4o-mini-search-preview","display_name":"gpt-4o-mini-search-preview","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"limit":{"context":128000,"output":128000},"metadata":{"description":"Using the Chat Completions API, you can directly access the fine-tuned models and tool used by Search in ChatGPT.\n\nWhen using Chat Completions, the model always retrieves information from the web before responding to your query. To use web_search_preview as a tool that models like gpt-4o and gpt-4o-mini invoke only when necessary, switch to using the Responses API.\n\nCurrently, you need to use one of these models to use web search in Chat Completions:\n\ngpt-4o-search-preview\ngpt-4o-mini-search-preview\nWeb search parameter example\nimport OpenAI from \"openai\";\nconst client = new OpenAI();\n\nconst completion = await client.chat.completions.create({\n    model: \"gpt-4o-search-preview\",\n    web_search_options: {},\n    messages: [{\n        \"role\": \"user\",\n        \"content\": \"What was a positive news story from today?\"\n    }],\n});\n\nconsole.log(completion.choices[0].message.content);\nOutput and citations\nThe API response item in the choices array will include:\n\nmessage.content with the text result from the model, inclusive of any inline citations\nannotations with a list of cited URLs\nBy default, the model's response will include inline citations for URLs found in the web search results. In addition to this, the url_citation annotation object will contain the URL and title of the cited source, as well as the start and end index characters in the model's response where those sources were used.","typeHints":["llm","search"],"features":["web","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"source":"public-provider-conf"},"vision":true},{"id":"jina-embeddings-v3","name":"jina-embeddings-v3","display_name":"jina-embeddings-v3","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"Text Embeddings Model, multilingual, 1024-dimensional, 570M parameters.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"mimo-v2-flash-free","name":"mimo-v2-flash-free","display_name":"mimo-v2-flash-free","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0,"output":0},"limit":{"context":256000,"output":256000},"metadata":{"description":"MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It adopts a MoE architecture with 309B total parameters and 15B active parameters per inference, balancing performance and efficiency. The model features a hybrid attention architecture, supports a hybrid-thinking toggle, and offers a 256K context window, enabling strong capabilities in complex reasoning, code generation, and agent-based scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks #1 among open-source models globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much.","typeHints":["llm"],"features":["web"],"inputModalities":["text"],"pricing":{"input":0,"output":0},"source":"public-provider-conf"},"vision":false},{"id":"ernie-4.5","name":"ernie-4.5","display_name":"ernie-4.5","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.068,"output":0.272},"limit":{"context":160000,"output":160000},"metadata":{"description":"Wenxin Large Model 4.5 is a next-generation native multimodal foundational model independently developed by Baidu. It achieves collaborative optimization through joint modeling of multiple modalities, demonstrating excellent multimodal understanding capabilities; it possesses more advanced language abilities, with comprehensive improvements in comprehension, generation, logic, and memory, as well as significant enhancements in hallucination reduction, logical reasoning, and coding capabilities.ERNIE-4.5-21B-A3B is an aligned open-source model with a MoE structure, having a total of 21 billion parameters and 3 billion activated parameters.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.068,"output":0.272},"source":"public-provider-conf"},"vision":true},{"id":"ernie-4.5-turbo-vl","name":"ernie-4.5-turbo-vl","display_name":"ernie-4.5-turbo-vl","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.4,"output":1.2},"limit":{"context":139000,"output":139000},"metadata":{"description":"The new version of the Wenxin Yiyan large model significantly improves capabilities in image understanding, creation, translation, and coding. It supports a context length of up to 32K tokens for the first time, with a notable reduction in the latency of the first token.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.4,"output":1.2},"source":"public-provider-conf"},"vision":true},{"id":"FLUX-1.1-pro","name":"FLUX-1.1-pro","display_name":"FLUX-1.1-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"FLUX-1.1-pro is an AI image generation tool for professional creators and content workflows. It understands complex semantic and structural instructions to deliver high consistency, multi-image coherence, and style customization from text prompts.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"o3-mini","name":"o3-mini","display_name":"o3-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"limit":{"context":200000,"output":200000},"metadata":{"description":"OpenAI's latest fast inference model excels at STEAM tasks and offers exceptional cost-effectiveness. Official support for cache hits reduces input prices by half.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":0.55,"input":1.1,"output":4.4},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"doubao-seed-1-6","name":"doubao-seed-1-6","display_name":"doubao-seed-1-6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.18,"output":1.8,"cache_read":0.036},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao-Seed-1.6 is a brand new multimodal deep reasoning model that supports four types of reasoning effort: minimal, low, medium, and high. It offers stronger model performance, serving complex tasks and challenging scenarios. It supports a 256k context window, with output length up to a maximum of 32k tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.036,"input":0.18,"output":1.8,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-1-6-flash","name":"doubao-seed-1-6-flash","display_name":"doubao-seed-1-6-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.044,"output":0.44,"cache_read":0.0088},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao-Seed-1.6-flash is an extremely fast multimodal deep thinking model, with TPOT requiring only 10ms. It supports both text and visual understanding, with its text comprehension skills surpassing the previous generation lite model and its visual understanding on par with competitor's pro series models. It supports a 256k context window and an output length of up to 16k tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.0088,"input":0.044,"output":0.44,"tiers":[{"cache_read":0.00411,"input":0.041096,"output":0.41096,"tier":{"size":32000,"type":"context"}},{"cache_read":0.00411,"input":0.082192,"output":0.82192,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-1-6-lite","name":"doubao-seed-1-6-lite","display_name":"doubao-seed-1-6-lite","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.082,"output":0.656,"cache_read":0.0164},"limit":{"context":256000,"output":256000},"metadata":{"description":"Doubao-Seed-1.6-lite is a brand new multimodal deep reasoning model that supports adjustable reasoning effort, with four modes: Minimal, Low, Medium, and High. It offers better cost performance, making it the best choice for common tasks, with a context window of up to 256k.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.0164,"input":0.082,"output":0.656,"tiers":[{"cache_read":0.00822,"input":0.0822,"output":0.548027,"tier":{"size":32000,"type":"context"}},{"cache_read":0.00822,"input":0.1644,"output":1.644,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-1-6-thinking","name":"doubao-seed-1-6-thinking","display_name":"doubao-seed-1-6-thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.18,"output":1.8,"cache_read":0.036},"limit":{"context":256000,"output":256000},"metadata":{"description":"The Doubao-Seed-1.6-thinking model has significantly enhanced reasoning capabilities. Compared with Doubao-1.5-thinking-pro, it has further improvements in fundamental abilities such as coding, mathematics, and logical reasoning, and now also supports visual understanding. It supports a 256k context window, with output length supporting up to 16k tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.036,"input":0.18,"output":1.8,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen3-30b-a3b-instruct-2507","name":"qwen3-30b-a3b-instruct-2507","display_name":"qwen3-30b-a3b-instruct-2507","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1028,"output":0.4112},"limit":{"context":8192,"output":8192},"metadata":{"description":"Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.\nMarkedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences.\nEnhanced 256K long-context understanding capabilities.","typeHints":["llm"],"pricing":{"input":0.1028,"output":0.4112},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-30b-a3b-thinking-2507","name":"qwen3-30b-a3b-thinking-2507","display_name":"qwen3-30b-a3b-thinking-2507","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.12,"output":1.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.\nMarkedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences.\nEnhanced 256K long-context understanding capabilities.","typeHints":["llm"],"pricing":{"input":0.12,"output":1.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gpt-oss-120b","name":"gpt-oss-120b","display_name":"gpt-oss-120b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.18,"output":0.9},"limit":{"context":131072,"output":131072},"metadata":{"description":"gpt-oss-120b is a 117B-parameter open-weight Mixture-of-Experts (MoE) language model from OpenAI, designed for high-reasoning, agentic, and general-purpose production use cases. Activating just 5.1B parameters per pass, it is optimized to run on a single H100 GPU with native MXFP4 quantization. The model features configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.18,"output":0.9},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen-3-235b-a22b-thinking-2507","name":"qwen-3-235b-a22b-thinking-2507","display_name":"qwen-3-235b-a22b-thinking-2507","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.28,"output":2.8},"limit":{"context":8192,"output":8192},"metadata":{"description":"cerebras","typeHints":["llm"],"pricing":{"input":0.28,"output":2.8},"source":"public-provider-conf"},"vision":false},{"id":"Qwen2-VL-72B-Instruct","name":"Qwen2-VL-72B-Instruct","display_name":"Qwen2-VL-72B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":2.18,"output":6.54},"limit":{"context":8192,"output":8192},"metadata":{"description":"The model provider is the Sophnet platform. Qwen2-VL-72B-Instruct is the latest iteration in the Qwen2-VL series launched by Alibaba Cloud, representing nearly a year of innovative achievements. This model has 72 billion parameters and can understand images of various resolutions and aspect ratios. Additionally, it supports video understanding of over 20 minutes, enabling high-quality video question answering, dialogue, and content creation, along with complex reasoning and decision-making capabilities.\n\n- State-of-the-art image understanding: capable of processing images of various resolutions and aspect ratios, performing excellently across multiple visual understanding benchmarks.\n- Long video understanding: supports video comprehension exceeding 20 minutes, enabling high-quality video Q&A, dialogues, and content creation.\n- Agent operation capability: equipped with complex reasoning and decision-making abilities, it can integrate with devices such as phones and robots to perform automated operations based on visual environments and textual instructions.\n- Multilingual support: in addition to English and Chinese, it supports understanding text in images in multiple languages, including most European languages, Japanese, Korean, Arabic, Vietnamese, and more.\n- Supports a maximum context length of 128K tokens, offering powerful processing capabilities.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"input":2.18,"output":6.54},"source":"public-provider-conf"},"vision":true},{"id":"Qwen2-VL-7B-Instruct","name":"Qwen2-VL-7B-Instruct","display_name":"Qwen2-VL-7B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.28,"output":0.7},"limit":{"context":8192,"output":8192},"metadata":{"description":"The model provider is the Sophnet platform. Qwen2-VL-7B-Instruct is the latest vision-language model launched by Alibaba Cloud and the newest member of the Qwen family. This model is proficient not only in recognizing common objects but also in analyzing text, charts, icons, and layouts within images. As a visual agent, it can reason and dynamically guide tool usage, supporting operations on computers and mobile phones. Additionally, it can understand long videos exceeding one hour and capture key events, accurately locate objects in images, and generate structured outputs for data such as invoices and tables, making it suitable for various scenarios including finance and business.\n\n- Vision understanding capability: not only recognizes common objects but also analyzes text, charts, icons, and layouts within images.\n- Agent capability: functions as a visual agent capable of reasoning and dynamically guiding tool usage, supporting operations on computers and mobile phones.\n- Long video understanding: can comprehend video content over one hour in length and accurately localize relevant video segments.\n- Visual localization: precisely locates objects within images by generating bounding boxes or points, providing stable JSON coordinate outputs.\n- Structured output: supports structured data output for invoices, tables, and other data, suitable for finance, business, and various other scenarios.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"input":0.28,"output":0.7},"source":"public-provider-conf"},"vision":true},{"id":"cc-kimi-for-coding","name":"cc-kimi-for-coding","display_name":"cc-kimi-for-coding","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"limit":{"context":8192,"output":8192},"metadata":{"description":"for claude code","typeHints":["llm"],"pricing":{"cache_read":0.02,"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"gemini-embedding-001","name":"gemini-embedding-001","display_name":"gemini-embedding-001","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.15,"output":0.15},"limit":{"context":8192,"output":8192},"metadata":{"description":"Latest version","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.15,"output":0.15},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen/Qwen3-30B-A3B","display_name":"Qwen/Qwen3-30B-A3B","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":1,"output":1},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by chutes.ai","typeHints":["llm"],"pricing":{"input":1,"output":1},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-32B","name":"Qwen/Qwen3-32B","display_name":"Qwen/Qwen3-32B","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.4,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.8},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-32b","name":"qwen3-32b","display_name":"qwen3-32b","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.16,"output":0.64},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.64},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-14B","name":"Qwen/Qwen3-14B","display_name":"Qwen/Qwen3-14B","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by chutes.ai","typeHints":["llm"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"Qwen/Qwen3-8B","name":"Qwen/Qwen3-8B","display_name":"Qwen/Qwen3-8B","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by chutes.ai","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"embedding-2","name":"embedding-2","display_name":"embedding-2","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.0686,"output":0.0686},"limit":{"context":8000,"output":8000},"metadata":{"description":"A text vector model that converts input text information into vector representations so that, in conjunction with a vector database, it provides an external knowledge base for the large model, thereby improving the accuracy of the model’s reasoning.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.0686,"output":0.0686},"source":"public-provider-conf"},"vision":false},{"id":"embedding-3","name":"embedding-3","display_name":"embedding-3","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.0686,"output":0.0686},"limit":{"context":8000,"output":8000},"metadata":{"description":"A text vector model that converts input text into vector representations to work with a vector database and provide an external knowledge base for a large model. The model supports custom vector dimensions; it is recommended to choose 256, 512, 1024, or 2048 dimensions.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.0686,"output":0.0686},"source":"public-provider-conf"},"vision":false},{"id":"gemini-2.5-pro-preview-06-05","name":"gemini-2.5-pro-preview-06-05","display_name":"gemini-2.5-pro-preview-06-05","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","audio","video"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Google’s latest multimodal flagship model, combining exceptional coding and reasoning capabilities. Its massive 1 million token context window (soon to expand to 2 million) places it at the top of the WebDevArena and LMArena leaderboards. It is particularly well-suited for developing aesthetically pleasing and highly functional interactive web applications, code transformation, and complex workflows. The newly introduced \"reasoning budget\" feature cleverly balances cost and performance, while optimized tool calls and response styles further enhance development efficiency, making it the ideal choice for rapid prototyping and advanced coding.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image","audio","video"],"pricing":{"cache_read":0.125,"input":1.25,"output":10,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen/Qwen2.5-VL-72B-Instruct","display_name":"Qwen/Qwen2.5-VL-72B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen2.5-VL is a visual language model from the Qwen2.5 series, equipped with strong visual understanding and reasoning capabilities. It can recognize objects, analyze text and charts, understand key events in long videos, and accurately locate targets within images. The model supports structured output, making it suitable for data such as invoices and forms, and performs excellently in multiple benchmark tests.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":true},{"id":"o1","name":"o1","display_name":"o1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":15,"output":60,"cache_read":7.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"OpenAI's most powerful O-series model supports official cache hits that halve the input cost.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text"],"pricing":{"cache_read":7.5,"input":15,"output":60},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o1-pro","name":"o1-pro","display_name":"o1-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":170,"output":680,"cache_read":170},"limit":{"context":8192,"output":8192},"metadata":{"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text"],"pricing":{"cache_read":170,"input":170,"output":680},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","display_name":"ByteDance-Seed/Seed-OSS-36B-Instruct","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.2,"output":0.534},"limit":{"context":256000,"output":256000},"metadata":{"description":"Seed-OSS is a series of open-source large language models developed by ByteDance's Seed team, designed specifically for powerful long-context processing, reasoning, agents, and general capabilities. Among this series, Seed-OSS-36B-Instruct is an instruction-tuned model with 36 billion parameters that natively supports ultra-long context lengths, enabling it to process massive documents or complex codebases in a single pass. This model is specially optimized for reasoning, code generation, and agent tasks (such as tool usage), while maintaining balanced and excellent general capabilities. A notable feature of this model is the \"Thinking Budget\" functionality, which allows users to flexibly adjust the inference length as needed, thereby effectively improving inference efficiency in practical applications.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.2,"output":0.534},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"doubao-seed-1-6-250615","name":"doubao-seed-1-6-250615","display_name":"doubao-seed-1-6-250615","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.18,"output":2.52,"cache_read":0.036},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-Seed-1.6 is a brand new multimodal deep reasoning model that supports four types of reasoning effort: minimal, low, medium, and high. It offers stronger model performance, serving complex tasks and challenging scenarios. It supports a 256k context window, with output length up to a maximum of 32k tokens.","typeHints":["llm"],"pricing":{"cache_read":0.036,"input":0.18,"output":2.52,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"doubao-seed-1-6-flash-250615","name":"doubao-seed-1-6-flash-250615","display_name":"doubao-seed-1-6-flash-250615","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.044,"output":0.44,"cache_read":0.0088},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-Seed-1.6-flash is an extremely fast multimodal deep thinking model, with TPOT requiring only 10ms. It supports both text and visual understanding, with its text comprehension skills surpassing the previous generation lite model and its visual understanding on par with competitor's pro series models. It supports a 256k context window and an output length of up to 16k tokens.","typeHints":["llm"],"pricing":{"cache_read":0.0088,"input":0.044,"output":0.44,"tiers":[{"cache_read":0.00411,"input":0.041096,"output":0.41096,"tier":{"size":32000,"type":"context"}},{"cache_read":0.00411,"input":0.082192,"output":0.82192,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"doubao-seed-1-6-thinking-250615","name":"doubao-seed-1-6-thinking-250615","display_name":"doubao-seed-1-6-thinking-250615","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.18,"output":2.52,"cache_read":0.036},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Doubao-Seed-1.6-thinking model has significantly enhanced reasoning capabilities. Compared with Doubao-1.5-thinking-pro, it has further improvements in fundamental abilities such as coding, mathematics, and logical reasoning, and now also supports visual understanding. It supports a 256k context window, with output length supporting up to 16k tokens.","typeHints":["llm"],"pricing":{"cache_read":0.036,"input":0.18,"output":2.52,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"doubao-seed-1-6-vision-250815","name":"doubao-seed-1-6-vision-250815","display_name":"doubao-seed-1-6-vision-250815","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.10959,"output":1.0959,"cache_read":0.021918},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-Seed-1.6-vision is a visual deep-thinking model that demonstrates stronger general multimodal understanding and reasoning capabilities in scenarios such as education, image moderation, inspection and security, and AI search Q&A. It supports a 256K context window and an output length of up to 64K tokens.","typeHints":["llm"],"pricing":{"cache_read":0.021918,"input":0.10959,"output":1.0959,"tiers":[{"cache_read":0.021863,"input":0.164384,"output":2.191239,"tier":{"size":32000,"type":"context"}},{"cache_read":0.022027,"input":0.328768,"output":3.28768,"tier":{"size":128000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-Prover-V2-671B","name":"deepseek-ai/DeepSeek-Prover-V2-671B","display_name":"deepseek-ai/DeepSeek-Prover-V2-671B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by chutes.ai\nDeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from DeepSeek-Prover-V1.5 Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description.","typeHints":["llm"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"gemini-2.5-flash-preview-tts","name":"gemini-2.5-flash-preview-tts","display_name":"gemini-2.5-flash-preview-tts","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemini 2.5 Flash Preview TTS is a lightweight, low-latency text-to-speech model designed for real-time voice generation. It produces natural, expressive speech with accurate control over tone, style, and pacing, while dynamically adjusting speaking speed based on context and instructions. The model also maintains consistent and distinguishable voices across multi-turn and multi-speaker conversations, making it well-suited for interactive and conversational applications that require stable, high-quality audio output.","typeHints":["tts"],"inputModalities":["text"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":false},{"id":"gemini-2.5-pro-preview-tts","name":"gemini-2.5-pro-preview-tts","display_name":"gemini-2.5-pro-preview-tts","type":"audio","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":1,"output":1},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemini 2.5 Pro Preview TTS is a high-fidelity text-to-speech model designed for premium voice experiences and complex speech generation scenarios. It delivers highly natural and expressive audio with precise control over tone, style, and emotional nuance, while maintaining smooth, context-aware pacing across long-form content. The model excels in multi-speaker and dialogue-heavy use cases, preserving consistent character voices and conversational coherence, making it well-suited for narration, storytelling, and advanced conversational AI applications.","typeHints":["tts"],"inputModalities":["text"],"pricing":{"input":1,"output":1},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemma-3-12b-it","name":"gemma-3-12b-it","display_name":"gemma-3-12b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"gemma-3-27b-it","name":"gemma-3-27b-it","display_name":"gemma-3-27b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"gemma-3-4b-it","name":"gemma-3-4b-it","display_name":"gemma-3-4b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"gemma-3n-e4b-it","name":"gemma-3n-e4b-it","display_name":"gemma-3n-e4b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets. This model includes innovations in parameter-efficient processing, including Per-Layer Embedding (PLE) parameter caching and a MatFormer model architecture that provides the flexibility to reduce compute and memory requirements. These models feature audio input handling, as well as text and visual data.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-1.5-thinking-pro","name":"Doubao-1.5-thinking-pro","display_name":"Doubao-1.5-thinking-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.62,"output":2.48},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-1.5 is a brand-new deep thinking model that excels in specialized fields such as mathematics, programming, scientific reasoning, and general tasks like creative writing. It achieves or approaches the top-tier industry level on multiple authoritative benchmarks including AIME 2024, Codeforces, and GPQA. It supports a 128k context window and 16k output.","typeHints":["llm"],"pricing":{"input":0.62,"output":2.48},"source":"public-provider-conf"},"vision":false},{"id":"cc-minimax-m2","name":"cc-minimax-m2","display_name":"cc-minimax-m2","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"gemma-3-1b-it","name":"gemma-3-1b-it","display_name":"gemma-3-1b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-r1-distill-llama-70b","name":"deepseek-r1-distill-llama-70b","display_name":"deepseek-r1-distill-llama-70b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.8,"output":1.6},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by Groq, the DeepSeek-R1-Distill model is fine-tuned based on an open-source model, using samples generated by DeepSeek-R1. We have made slight modifications to their configurations and tokenizers. Please use our settings to run these models.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text"],"pricing":{"input":0.8,"output":1.6},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-4o-mini-tts","name":"gpt-4o-mini-tts","display_name":"gpt-4o-mini-tts","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.6,"output":12},"limit":{"context":8192,"output":8192},"metadata":{"description":"OpenAI’s latest TTS model, gpt-4o-mini-tts, uses the same API endpoint (/v1/audio/speech) as tts-1. However, OpenAI introduced a new pricing method without providing billing details via API, causing discrepancies between official pricing and aihubmix’s charges—some requests may cost more, others less. Avoid using this model if precise billing accuracy is essential.","typeHints":["tts"],"inputModalities":["text"],"pricing":{"input":0.6,"output":12},"source":"public-provider-conf"},"vision":false},{"id":"tngtech/DeepSeek-R1T-Chimera","name":"tngtech/DeepSeek-R1T-Chimera","display_name":"tngtech/DeepSeek-R1T-Chimera","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by chutes.ai\nDeepSeek-R1T-Chimera merges DeepSeek-R1’s reasoning strengths with DeepSeek-V3 (0324)’s token-efficiency improvements into a MoE Transformer optimized for general text generation. It integrates pretrained weights from both models and is released under the MIT license for research and commercial use.","typeHints":["llm"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"o1-preview","name":"o1-preview","display_name":"o1-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":15,"output":60,"cache_read":7.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"The latest and most powerful inference model from OpenAI; AiHubMix uses both OpenAI and Microsoft Azure OpenAI channels simultaneously to achieve high-concurrency load balancing.","typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":7.5,"input":15,"output":60},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o1-mini","name":"o1-mini","display_name":"o1-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":3,"output":12,"cache_read":1.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"o1-mini is faster and 80% cheaper, and is competitive with o1-preview on coding tasks. AiHubMix uses both OpenAI and Microsoft Azure OpenAI channels simultaneously.","typeHints":["llm"],"pricing":{"cache_read":1.5,"input":3,"output":12},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4o-2024-11-20","name":"gpt-4o-2024-11-20","display_name":"gpt-4o-2024-11-20","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":128000,"output":128000},"metadata":{"description":"The latest version of the GPT-4o model; it is recommended to use this version, as it is currently smarter than the regular 4o.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":1.25,"input":2.5,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"gpt-4o","name":"gpt-4o","display_name":"gpt-4o","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","pdf"]},"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":128000,"output":128000},"metadata":{"description":"GPT-4o (“o” stands for “omni”) is a new-generation multimodal model designed for more natural human–computer interaction. It can accept any combination of text, audio, image, and video as input, and generate multimodal outputs including text, audio, and images. With audio response latency as low as 232 milliseconds on average around 320 milliseconds, it approaches real human conversational speed. The model delivers strong performance in English text and code, significantly improved multilingual understanding, and outstanding capabilities in visual and audio perception, while offering faster API performance and substantially reduced cost for real-time and complex multimodal applications.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","pdf"],"pricing":{"cache_read":1.25,"input":2.5,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"gpt-4o-mini","name":"gpt-4o-mini","display_name":"gpt-4o-mini","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"limit":{"context":128000,"output":128000},"metadata":{"description":"The lightweight version of GPT-4o, which is affordable and fast, suitable for handling simple tasks; our site supports the official automatic caching for this model, and charges for cache hits will be automatically halved.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"source":"public-provider-conf"},"vision":true},{"id":"AiHubmix-mistral-medium","name":"AiHubmix-mistral-medium","display_name":"AiHubmix-mistral-medium","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Mistral Medium 3 is a SOTA & versatile model designed for a wide range of tasks, including programming, mathematical reasoning, understanding long documents, summarization, and dialogue.\n\nIt boasts multi-modal capabilities, enabling it to process visual inputs, and supports dozens of languages, including over 80 coding languages. Additionally, it features function calling and agentic workflows.\n\nMistral Medium 3 is optimized for single-node inference, particularly for long-context applications. Its size allows it to achieve high throughput on a single node.","typeHints":["llm"],"pricing":{"input":0.4,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"ERNIE-X1.1-Preview","name":"ERNIE-X1.1-Preview","display_name":"ERNIE-X1.1-Preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.136,"output":0.544},"limit":{"context":119000,"output":119000},"metadata":{"description":"The Wenxin large model X1.1 has made significant improvements in question answering, tool invocation, intelligent agents, instruction following, logical reasoning, mathematics, and coding tasks, with notable enhancements in factual accuracy. The context length has been extended to 64K tokens, supporting longer inputs and dialogue history, which improves the coherence of long-chain reasoning while maintaining response speed.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.136,"output":0.544},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Qwen/QwQ-32B","name":"Qwen/QwQ-32B","display_name":"Qwen/QwQ-32B","type":"chat","reasoning":{"supported":true},"tool_call":true,"cost":{"input":0.14,"output":0.56},"limit":{"context":8192,"output":8192},"metadata":{"description":"Silicon-based flow provision","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"pricing":{"input":0.14,"output":0.56},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"chutesai/Mistral-Small-3.1-24B-Instruct-2503","name":"chutesai/Mistral-Small-3.1-24B-Instruct-2503","display_name":"chutesai/Mistral-Small-3.1-24B-Instruct-2503","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"description":"Mistral's latest open-source small model; provided by chutes.ai.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"ernie-x1.1-preview","name":"ernie-x1.1-preview","display_name":"ernie-x1.1-preview","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.136,"output":0.544},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Wenxin large model X1.1 has made significant improvements in question answering, tool invocation, intelligent agents, instruction following, logical reasoning, mathematics, and coding tasks, with notable enhancements in factual accuracy. The context length has been extended to 64K tokens, supporting longer inputs and dialogue history, which improves the coherence of long-chain reasoning while maintaining response speed.","typeHints":["llm"],"pricing":{"input":0.136,"output":0.544},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"ernie-4.5-0.3b","name":"ernie-4.5-0.3b","display_name":"ernie-4.5-0.3b","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.0136,"output":0.0544},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wenxin Large Model 4.5 is a next-generation native multimodal foundational large model independently developed by Baidu. It achieves collaborative optimization through joint modeling of multiple modalities, demonstrating excellent multimodal understanding capabilities. The model possesses enhanced language abilities, with comprehensive improvements in understanding, generation, reasoning, and memory. It significantly reduces hallucinations and shows notable advancements in logical reasoning and coding skills.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.0136,"output":0.0544},"source":"public-provider-conf"},"vision":true},{"id":"ernie-4.5-turbo-128k-preview","name":"ernie-4.5-turbo-128k-preview","display_name":"ernie-4.5-turbo-128k-preview","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.108,"output":0.432},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wenxin 4.5 Turbo also shows significant enhancements in reducing hallucinations, logical reasoning, and coding capabilities. Compared to Wenxin 4.5, it is faster and more cost-effective.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.108,"output":0.432},"source":"public-provider-conf"},"vision":true},{"id":"ernie-x1-turbo","name":"ernie-x1-turbo","display_name":"ernie-x1-turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.136,"output":0.544},"limit":{"context":50500,"output":50500},"metadata":{"description":"Wenxin Large Model X1 possesses enhanced abilities in understanding, planning, reflection, and evolution. As a more comprehensive deep-thinking model, Wenxin X1 combines accuracy, creativity, and literary elegance, excelling particularly in Chinese knowledge Q&A, literary creation, document writing, daily conversations, logical reasoning, complex calculations, and tool invocation.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.136,"output":0.544},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"kat-dev","name":"kat-dev","display_name":"kat-dev","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.137,"output":0.548},"limit":{"context":128000,"output":128000},"metadata":{"description":"KAT-Dev (32B) is an open-source 32B parameter model specifically designed for software engineering tasks. It achieved a 62.4% resolution rate on the SWE-Bench Verified benchmark, ranking fifth among all open-source models of various scales. The model is optimized through multiple stages, including intermediate training, supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT), as well as large-scale agent reinforcement learning (RL). Based on Qwen3-32B, its training process lays the foundation for subsequent fine-tuning and reinforcement learning stages by enhancing fundamental abilities such as tool usage, multi-turn interaction, and instruction following. During the fine-tuning phase, the model not only learns eight carefully curated task types and programming scenarios but also innovatively introduces a reinforcement fine-tuning (RFT) stage guided by human engineer-annotated “teacher trajectories.” The final agent reinforcement learning phase addresses scalability challenges through multi-level prefix caching, entropy-based trajectory pruning, and efficient architecture.","typeHints":["llm"],"features":["tools"],"inputModalities":["text"],"pricing":{"input":0.137,"output":0.548},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.3-70b","name":"llama-3.3-70b","display_name":"llama-3.3-70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.6,"output":0.6},"limit":{"context":65536,"output":65536},"metadata":{"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.","typeHints":["llm"],"pricing":{"input":0.6,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/Kimi-Dev-72B","name":"moonshotai/Kimi-Dev-72B","display_name":"moonshotai/Kimi-Dev-72B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.32,"output":1.28},"limit":{"context":8192,"output":8192},"metadata":{"description":"Kimi-Dev-72B is a new generation open-source programming large model that achieved a leading performance of 60.4% on SWE-bench Verified. Through large-scale reinforcement learning optimization, it can automatically fix code in real Docker environments, receiving rewards only when passing the complete test suite, thereby ensuring the correctness and robustness of solutions and aligning more closely with real software development standards.","typeHints":["llm"],"pricing":{"input":0.32,"output":1.28},"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/Moonlight-16B-A3B-Instruct","name":"moonshotai/Moonlight-16B-A3B-Instruct","display_name":"moonshotai/Moonlight-16B-A3B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by chutes.ai.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"nvidia-nemotron-3-super-120b-a12b","name":"nvidia-nemotron-3-super-120b-a12b","display_name":"nvidia-nemotron-3-super-120b-a12b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.11,"output":0.55,"cache_read":0.0275},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"An open-source, efficient hybrid Mamba-Transformer MoE model that supports a context length of one million tokens and excels at agent reasoning, programming, planning, and tool invocation.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text"],"pricing":{"cache_read":0.0275,"input":0.11,"output":0.55},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"o1-global","name":"o1-global","display_name":"o1-global","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":15,"output":60,"cache_read":7.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"OpenAI new model","typeHints":["llm"],"pricing":{"cache_read":7.5,"input":15,"output":60},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qianfan-qi-vl","name":"qianfan-qi-vl","display_name":"qianfan-qi-vl","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qianfan-QI-VL model is a proprietary image quality inspection and visual understanding large model (Quality Inspection Large Vision Language Model, Qianfan-QI-VL) developed by Baidu Cloud’s Qianfan platform. It is designed for quality inspection of product images uploaded in e-commerce scenarios, with detection capabilities including AIGC human defect detection, mosaic recognition, watermark recognition, and trademark detection.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-vl-72b-instruct","name":"qwen2.5-vl-72b-instruct","display_name":"qwen2.5-vl-72b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2.4,"output":7.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Strong capability in Chinese domain recognition, comparable to ChatGPT-4.0.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":2.4,"output":7.2},"source":"public-provider-conf"},"vision":true},{"id":"tencent/Hunyuan-A13B-Instruct","name":"tencent/Hunyuan-A13B-Instruct","display_name":"tencent/Hunyuan-A13B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.14,"output":0.56},"limit":{"context":8192,"output":8192},"metadata":{"description":"Hunyuan-A13B-Instruct has 8 billion parameters and can match larger models by activating only 1.3 billion parameters, supporting \"fast thinking/slow thinking\" hybrid inference. It offers stable long text understanding. Verified by BFCL-v3 and τ-Bench, its Agent capabilities are leading in the field. Combined with GQA and multiple quantization formats, it enables efficient inference.","typeHints":["llm"],"pricing":{"input":0.14,"output":0.56},"source":"public-provider-conf"},"vision":false},{"id":"unsloth/gemma-3-27b-it","name":"unsloth/gemma-3-27b-it","display_name":"unsloth/gemma-3-27b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.22,"output":0.22},"limit":{"context":8192,"output":8192},"metadata":{"description":"Google's latest open-source model; provided by chutes.ai","typeHints":["llm"],"pricing":{"input":0.22,"output":0.22},"source":"public-provider-conf"},"vision":false},{"id":"MiniMaxAI/MiniMax-M1-80k","name":"MiniMaxAI/MiniMax-M1-80k","display_name":"MiniMaxAI/MiniMax-M1-80k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.6,"output":2.4},"limit":{"context":8192,"output":8192},"metadata":{"description":"MiniMax-M1 is an open-source large-scale hybrid attention model with 456B total parameters (45.9B activated per token). It natively supports 1M-token context and reduces FLOPs by 75% versus DeepSeek R1 in 100K-token generation tasks via lightning attention. Built on MoE architecture and optimized by CISPO algorithm, it achieves state-of-the-art performance in long-context reasoning and real-world software engineering scenarios.","typeHints":["llm"],"pricing":{"input":0.6,"output":2.4},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen/Qwen2.5-VL-32B-Instruct","display_name":"Qwen/Qwen2.5-VL-32B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image","video"]},"cost":{"input":0.24,"output":0.24},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen2.5-VL-32B-Instruct is an advanced multimodal model from the Tongyi Qianwen team that can recognize objects, analyze text and graphics in images, operate tools, locate objects in images, and generate structured outputs. Through reinforcement learning, it has improved mathematics and problem-solving capabilities, with a more concise and natural response style.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image","video"],"pricing":{"input":0.24,"output":0.24},"source":"public-provider-conf"},"vision":true},{"id":"baidu/ERNIE-4.5-300B-A47B","name":"baidu/ERNIE-4.5-300B-A47B","display_name":"baidu/ERNIE-4.5-300B-A47B","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.32,"output":1.28},"limit":{"context":8192,"output":8192},"metadata":{"description":"ERNIE-4.5-300B-A47B is a large language model developed by Baidu based on a Mixture of Experts (MoE) architecture. The model has a total of 300 billion parameters, but only activates 47 billion parameters per token during inference, which balances strong performance with computational efficiency. As one of the core models in the ERNIE 4.5 series, it demonstrates outstanding capabilities in tasks such as text understanding, generation, reasoning, and programming. The model employs an innovative multimodal heterogeneous MoE pretraining approach, leveraging joint training of textual and visual modalities to effectively enhance the model’s overall abilities, particularly excelling in instruction following and world knowledge memorization. Baidu has open-sourced this model along with other models in the series, aiming to promote the research and application of AI technology.","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.32,"output":1.28},"source":"public-provider-conf"},"vision":true},{"id":"bge-large-en","name":"bge-large-en","display_name":"bge-large-en","type":"embedding","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.068,"output":0.068},"limit":{"context":8192,"output":8192},"metadata":{"description":"bge-large-en, open-sourced by the Beijing Academy of Artificial Intelligence (BAAI), is currently the most powerful vector representation model for Chinese tasks, with its semantic representation capabilities comprehensively surpassing those of similar open-source models.","typeHints":["embedding"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.068,"output":0.068},"source":"public-provider-conf"},"vision":true},{"id":"bge-large-zh","name":"bge-large-zh","display_name":"bge-large-zh","type":"embedding","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.068,"output":0.068},"limit":{"context":8192,"output":8192},"metadata":{"description":"bge-large-zh, open-sourced by the Beijing Academy of Artificial Intelligence (BAAI), is currently the most powerful vector representation model for Chinese tasks, with its semantic representation capabilities comprehensively surpassing those of similar open-source models.","typeHints":["embedding"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.068,"output":0.068},"source":"public-provider-conf"},"vision":true},{"id":"codestral-latest","name":"codestral-latest","display_name":"codestral-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":1.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Mistral has launched a new code model - Codestral 25.01; https://mistral.ai/news/codestral-2501/","typeHints":["llm"],"pricing":{"input":0.4,"output":1.2},"source":"public-provider-conf"},"vision":false},{"id":"gemini-exp-1206","name":"gemini-exp-1206","display_name":"gemini-exp-1206","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.25,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Google's latest experimental model, currently Google's most powerful model.","typeHints":["llm"],"pricing":{"input":1.25,"output":5},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4o-zh","name":"gpt-4o-zh","display_name":"gpt-4o-zh","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":2.5,"output":10},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":2.5,"output":10},"source":"public-provider-conf"},"vision":true},{"id":"qwen-qwq-32b","name":"qwen-qwq-32b","display_name":"qwen-qwq-32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"unsloth/gemma-3-12b-it","name":"unsloth/gemma-3-12b-it","display_name":"unsloth/gemma-3-12b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"description":"Provided by chutes.ai.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"qwen-max-0125","name":"qwen-max-0125","display_name":"qwen-max-0125","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.38,"output":1.52},"limit":{"context":8192,"output":8192},"metadata":{"description":"Qwen 2.5-Max latest model","typeHints":["llm"],"pricing":{"input":0.38,"output":1.52},"source":"public-provider-conf"},"vision":false},{"id":"tencent/Hunyuan-MT-7B","name":"tencent/Hunyuan-MT-7B","display_name":"tencent/Hunyuan-MT-7B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Hunyuan-MT-7B is a lightweight translation model with 7 billion parameters, designed to translate source text into target languages. The model supports translation among 33 languages as well as 5 Chinese minority languages. In the WMT25 International Machine Translation Competition, Hunyuan-MT-7B achieved first place in 30 out of 31 language categories it participated in, demonstrating its exceptional translation capabilities. For translation scenarios, Tencent Hunyuan proposed a complete training paradigm from pre-training to supervised fine-tuning, followed by translation reinforcement and ensemble reinforcement, enabling it to achieve industry-leading performance among models of similar scale. The model is computationally efficient, easy to deploy, and suitable for various application scenarios.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"BAAI/bge-large-en-v1.5","name":"BAAI/bge-large-en-v1.5","display_name":"BAAI/bge-large-en-v1.5","type":"embedding","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.034,"output":0.034},"limit":{"context":8192,"output":8192},"metadata":{"description":"BAAI/bge-large-en-v1.5 is a large English text embedding model and part of the BGE (BAAI General Embedding) series. It achieves excellent performance on the MTEB benchmark, with an average score of 64.23 across 56 datasets, excelling in tasks such as retrieval, clustering, and text pair classification. The model supports a maximum input length of 512 tokens and is suitable for various natural language processing tasks, such as text retrieval and semantic similarity computation.","typeHints":["embedding"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.034,"output":0.034},"source":"public-provider-conf"},"vision":true},{"id":"BAAI/bge-large-zh-v1.5","name":"BAAI/bge-large-zh-v1.5","display_name":"BAAI/bge-large-zh-v1.5","type":"embedding","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.034,"output":0.034},"limit":{"context":8192,"output":8192},"metadata":{"description":"BAAI/bge-large-zh-v1.5 is a large Chinese text embedding model and part of the BGE (BAAI General Embedding) series. It performs excellently on the C-MTEB benchmark, achieving an average score of 64.53 across 31 datasets, with outstanding results in tasks such as retrieval, semantic similarity, and text pair classification. The model supports a maximum input length of 512 tokens and is suitable for various Chinese natural language processing tasks, such as text retrieval and semantic similarity computation.","typeHints":["embedding"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.034,"output":0.034},"source":"public-provider-conf"},"vision":true},{"id":"kimi-thinking-preview","name":"kimi-thinking-preview","display_name":"kimi-thinking-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":30,"output":30},"limit":{"context":8192,"output":8192},"metadata":{"description":"The latest kimi model.","typeHints":["llm"],"pricing":{"input":30,"output":30},"source":"public-provider-conf"},"vision":false},{"id":"doubao-embedding-large-text-240915","name":"doubao-embedding-large-text-240915","display_name":"doubao-embedding-large-text-240915","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"description":"doubao-embedding-large-text-240915\nDoubao Embedding is a semantic vectorization model developed by ByteDance, primarily designed for vector search scenarios. It supports both Chinese and English languages and has a maximum context length of approximately 4K tokens.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4o-2024-08-06","name":"gpt-4o-2024-08-06","display_name":"gpt-4o-2024-08-06","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":8192,"output":8192},"metadata":{"description":"Supports caching, with automatic halving of charges upon a cache hit.","typeHints":["llm"],"pricing":{"cache_read":1.25,"input":2.5,"output":10},"source":"public-provider-conf"},"vision":false},{"id":"qwen-plus-2025-07-28","name":"qwen-plus-2025-07-28","display_name":"qwen-plus-2025-07-28","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.1126,"output":1.126,"cache_read":0.02252},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Tongyi Qianwen series balanced capability model has inference performance and speed between Tongyi Qianwen-Max and Tongyi Qianwen-Turbo, making it suitable for moderately complex tasks. This model adopts tiered pricing.","typeHints":["llm"],"pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-plus-latest","name":"qwen-plus-latest","display_name":"qwen-plus-latest","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.1126,"output":1.126,"cache_read":0.02252},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen series models with balanced capabilities have inference performance and speed between Qwen-Max and Qwen-Turbo, making them suitable for moderately complex tasks. This model is a dynamically updated version, and updates will not be announced in advance. The current version is qwen-plus-2025-04-28.The model adopts tiered pricing.","typeHints":["llm"],"pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"stepfun-ai/step3","name":"stepfun-ai/step3","display_name":"stepfun-ai/step3","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.1,"output":2.75},"limit":{"context":8192,"output":8192},"metadata":{"description":"Step3 is a multimodal reasoning model released by StepFun. It uses a Mixture‑of‑Experts (MoE) architecture with 321 billion total parameters and 38 billion activation parameters. The model follows an end‑to‑end design that reduces decoding cost while delivering top‑tier performance on vision‑language reasoning tasks. Thanks to the combined use of Multi‑Head Factorized Attention (MFA) and Attention‑FFN Decoupling (AFD), Step3 remains highly efficient on both flagship and low‑end accelerators. During pre‑training, it processed over 20 trillion text tokens and 4 trillion image‑text mixed tokens, covering more than ten languages. On benchmarks for mathematics, code, and multimodal tasks, Step3 consistently outperforms other open‑source models.","typeHints":["llm"],"pricing":{"input":1.1,"output":2.75},"source":"public-provider-conf"},"vision":false},{"id":"text-embedding-v4","name":"text-embedding-v4","display_name":"text-embedding-v4","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.08,"output":0.08},"limit":{"context":8192,"output":8192},"metadata":{"description":"This is the Tongyi Laboratory's multilingual unified text vector model trained based on Qwen3, which significantly improves performance in text retrieval, clustering, and classification compared to version V3; it achieves a 15% to 40% improvement on evaluation tasks such as MTEB multilingual, Chinese-English, and code retrieval; supports user-defined vector dimensions ranging from 64 to 2048.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.08,"output":0.08},"source":"public-provider-conf"},"vision":false},{"id":"qwen-turbo-latest","name":"qwen-turbo-latest","display_name":"qwen-turbo-latest","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.046,"output":0.092,"cache_read":0.0092},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen series model with the fastest speed and lowest cost, suitable for simple tasks. This model is a dynamically updated version, and updates will not be announced in advance. The model's overall Chinese and English abilities have been significantly improved, human preference alignment has been greatly enhanced, inference capability and complex instruction understanding have been substantially strengthened, performance on difficult tasks is better, and mathematics and coding skills have been significantly improved. The current version is qwen-turbo-2025-04-28.","typeHints":["llm"],"pricing":{"cache_read":0.0092,"input":0.046,"output":0.092},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"AiHubmix-Phi-4-mini-reasoning","name":"AiHubmix-Phi-4-mini-reasoning","display_name":"AiHubmix-Phi-4-mini-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.12,"output":0.12},"limit":{"context":128000,"output":128000},"metadata":{"description":"Phi-4-mini-reasoning is a lightweight open model designed for advanced mathematical reasoning and logic-intensive problem-solving. It is particularly well-suited for tasks such as formal proofs, symbolic computation, and solving multi-step word problems. With its efficient architecture, the model balances high-quality reasoning performance with cost-effective deployment, making it ideal for educational applications, embedded tutoring, and lightweight edge or mobile systems.\n\nPhi-4-mini-reasoning supports a 128K token context length, enabling it to process and reason over long mathematical problems and proofs. Built on synthetic and high-quality math datasets, the model leverages advanced fine-tuning techniques such as supervised fine-tuning and preference modeling to enhance reasoning capabilities. Its training incorporates safety and alignment protocols, ensuring robust and reliable performance across supported use cases.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.12,"output":0.12},"source":"public-provider-conf"},"vision":false},{"id":"aihub-Phi-4-multimodal-instruct","name":"aihub-Phi-4-multimodal-instruct","display_name":"aihub-Phi-4-multimodal-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","audio"]},"cost":{"input":0.12,"output":0.48},"limit":{"context":128000,"output":128000},"metadata":{"description":"Microsoft's latest model","typeHints":["llm"],"inputModalities":["text","image","audio"],"pricing":{"input":0.12,"output":0.48},"source":"public-provider-conf"},"vision":true},{"id":"qwen3-30b-a3b","name":"qwen3-30b-a3b","display_name":"qwen3-30b-a3b","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.12,"output":1.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Achieves effective integration of thinking and non-thinking modes, allowing mode switching during conversations. Its reasoning ability matches that of QwQ-32B with a smaller parameter size, and its general capability significantly surpasses Qwen2.5-14B, reaching state-of-the-art (SOTA) levels among industry models of the same scale.","typeHints":["llm"],"pricing":{"input":0.12,"output":1.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"aihub-Phi-4-mini-instruct","name":"aihub-Phi-4-mini-instruct","display_name":"aihub-Phi-4-mini-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.12,"output":0.48},"limit":{"context":128000,"output":128000},"metadata":{"description":"Microsoft's latest model","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.12,"output":0.48},"source":"public-provider-conf"},"vision":false},{"id":"grok-3","name":"grok-3","display_name":"grok-3","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":3,"output":15},"limit":{"context":8192,"output":8192},"metadata":{"description":"Grok's latest model","typeHints":["llm"],"pricing":{"input":3,"output":15},"source":"public-provider-conf"},"vision":false},{"id":"grok-3-beta","name":"grok-3-beta","display_name":"grok-3-beta","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":3,"output":15},"limit":{"context":8192,"output":8192},"metadata":{"description":"Grok's latest model\nThis model ID with beta has been officially taken offline. Using this model grok-3-beta will automatically point to grok-3.","typeHints":["llm"],"pricing":{"input":3,"output":15},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-14b","name":"qwen3-14b","display_name":"qwen3-14b","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.16,"output":1.6},"limit":{"context":8192,"output":8192},"metadata":{"description":"Achieves effective integration of thinking and non-thinking modes, enabling mode switching during conversations. Its reasoning ability reaches state-of-the-art (SOTA) levels among models of the same scale, and its general capability significantly surpasses Qwen2.5-14B.","typeHints":["llm"],"pricing":{"input":0.16,"output":1.6},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"doubao-embedding-text-240715","name":"doubao-embedding-text-240715","display_name":"doubao-embedding-text-240715","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.7,"output":0.7},"limit":{"context":8192,"output":8192},"metadata":{"description":"doubao-embedding-text-240715\nDoubao Embedding is a semantic vectorization model developed by ByteDance, primarily designed for vector search scenarios. It supports both Chinese and English languages and has a maximum context length of approximately 4K tokens.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.7,"output":0.7},"source":"public-provider-conf"},"vision":false},{"id":"aihub-Phi-4","name":"aihub-Phi-4","display_name":"aihub-Phi-4","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.12,"output":0.48},"limit":{"context":16400,"output":16400},"metadata":{"description":"Phi-4 is a state-of-the-art open model based on a combination of synthetic datasets, curated public domain website data, and acquired academic books and QA datasets. The approach aims to ensure that small, efficient models are trained using data focused on high quality and advanced reasoning.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.12,"output":0.48},"source":"public-provider-conf"},"vision":false},{"id":"claude-3-opus-20240229","name":"claude-3-opus-20240229","display_name":"claude-3-opus-20240229","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":16.5,"output":82.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Claude’s previous generation strongest model","typeHints":["llm"],"pricing":{"input":16.5,"output":82.5},"source":"public-provider-conf"},"vision":false},{"id":"dall-e-3","name":"dall-e-3","display_name":"dall-e-3","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"dall-e-3 is an AI image generation model that converts natural language prompts into realistic visuals and artistic content. It delivers accurate semantic understanding, supports customizable output resolutions, and produces high-quality images across a wide range of styles, making it well-suited for concept design, creative prototyping, and professional content workflows.","typeHints":["image_generation"],"inputModalities":["text","image"],"source":"public-provider-conf"},"vision":true},{"id":"qwen3-8b","name":"qwen3-8b","display_name":"qwen3-8b","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.08,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"description":"Achieves effective integration of thinking and non-thinking modes, enabling mode switching during conversations. Its reasoning ability reaches state-of-the-art (SOTA) levels among models of the same scale, and its general capability significantly surpasses Qwen2.5-7B.","typeHints":["llm"],"pricing":{"input":0.08,"output":0.8},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"grok-3-fast","name":"grok-3-fast","display_name":"grok-3-fast","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":5.5,"output":27.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":5.5,"output":27.5},"source":"public-provider-conf"},"vision":false},{"id":"grok-3-fast-beta","name":"grok-3-fast-beta","display_name":"grok-3-fast-beta","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":5.5,"output":27.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":5.5,"output":27.5},"source":"public-provider-conf"},"vision":false},{"id":"grok-3-mini","name":"grok-3-mini","display_name":"grok-3-mini","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.3,"output":0.501},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.3,"output":0.501},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-4b","name":"qwen3-4b","display_name":"qwen3-4b","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.046,"output":0.46},"limit":{"context":8192,"output":8192},"metadata":{"description":"Achieves effective integration of thinking and non-thinking modes, allowing mode switching during conversations. Its reasoning ability reaches state-of-the-art (SOTA) levels among models of the same scale, with significantly enhanced human preference alignment. There are notable improvements in creative writing, role-playing, multi-turn dialogue, and instruction following, resulting in a noticeably better user experience.","typeHints":["llm"],"pricing":{"input":0.046,"output":0.46},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek-ai/DeepSeek-R1-Zero","name":"deepseek-ai/DeepSeek-R1-Zero","display_name":"deepseek-ai/DeepSeek-R1-Zero","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.2,"output":2.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Openly deployed by chutes.ai; inference with FP8; zero is the initial preliminary version of R1 without optimizations and is not recommended for use unless for research purposes.","typeHints":["llm"],"pricing":{"input":2.2,"output":2.2},"source":"public-provider-conf"},"vision":false},{"id":"grok-3-mini-beta","name":"grok-3-mini-beta","display_name":"grok-3-mini-beta","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.33,"output":0.5511},"limit":{"context":8192,"output":8192},"metadata":{"description":"This model ID with beta has been officially taken offline. Using this model grok-3-mini-beta will automatically point to grok-3-mini.","typeHints":["llm"],"pricing":{"input":0.33,"output":0.5511},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-1.7b","name":"qwen3-1.7b","display_name":"qwen3-1.7b","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.046,"output":0.46},"limit":{"context":8192,"output":8192},"metadata":{"description":"Effectively integrates thinking and non-thinking modes, allowing mode switching during conversations. Its general capabilities significantly surpass those of the Qwen2.5 small-scale series, with greatly enhanced human preference alignment. There are notable improvements in creative writing, role-playing, multi-turn dialogue, and instruction following, resulting in a significantly better expected user experience.","typeHints":["llm"],"pricing":{"input":0.046,"output":0.46},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen3-0.6b","name":"qwen3-0.6b","display_name":"qwen3-0.6b","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.046,"output":0.46},"limit":{"context":8192,"output":8192},"metadata":{"description":"Effectively integrates thinking and non-thinking modes, allowing mode switching during conversations. Its general capabilities significantly surpass those of the Qwen2.5 small-scale series.","typeHints":["llm"],"pricing":{"input":0.046,"output":0.46},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-turbo-2025-04-28","name":"qwen-turbo-2025-04-28","display_name":"qwen-turbo-2025-04-28","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.046,"output":0.092},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen3 series Turbo model effectively integrates thinking and non-thinking modes, allowing seamless switching between modes during conversations. With a smaller parameter size, its reasoning ability rivals that of QwQ-32B, and its general capabilities significantly surpass those of Qwen2.5-Turbo, reaching state-of-the-art (SOTA) levels among models of the same scale. This version is a snapshot model as of April 28, 2025.","typeHints":["llm"],"pricing":{"input":0.046,"output":0.092},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"alicloud-glm-5","name":"alicloud-glm-5","display_name":"alicloud-glm-5","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.5634,"output":2.5353,"cache_read":0.11268},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-5 is an advanced, open-source large language model designed for developers tackling the toughest challenges. It excels at long-context reasoning, multi-step tool orchestration, and complex systems engineering, making it the ideal choice for powering sophisticated agents and applications that require high-level cognitive tasks.","typeHints":["llm"],"pricing":{"cache_read":0.11268,"input":0.5634,"output":2.5353,"tiers":[{"cache_read":0.16892,"input":0.8446,"output":3.096869,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"command-a-03-2025","name":"command-a-03-2025","display_name":"command-a-03-2025","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":2.5,"output":10},"limit":{"context":256000,"output":256000},"metadata":{"description":"Command A is Cohere most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":2.5,"output":10},"source":"public-provider-conf"},"vision":false},{"id":"grok-3-mini-fast-beta","name":"grok-3-mini-fast-beta","display_name":"grok-3-mini-fast-beta","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.33,"output":2.20011},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.33,"output":2.20011},"source":"public-provider-conf"},"vision":false},{"id":"qwen-3-32b","name":"qwen-3-32b","display_name":"qwen-3-32b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":1.6},"limit":{"context":8192,"output":8192},"metadata":{"description":"cerebras","typeHints":["llm"],"pricing":{"input":0.4,"output":1.6},"source":"public-provider-conf"},"vision":false},{"id":"qwen-plus-2025-04-28","name":"qwen-plus-2025-04-28","display_name":"qwen-plus-2025-04-28","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.1126,"output":1.126,"cache_read":0.02252},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen3 series Plus model effectively integrates thinking and non-thinking modes, allowing for mode switching during conversations. Its reasoning abilities significantly surpass those of QwQ, and its general capabilities are markedly superior to Qwen2.5-Plus, reaching state-of-the-art (SOTA) levels among models of the same scale. This version is a snapshot model as of April 28, 2025.","typeHints":["llm"],"pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"THUDM/GLM-Z1-32B-0414","name":"THUDM/GLM-Z1-32B-0414","display_name":"THUDM/GLM-Z1-32B-0414","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.08,"output":0.08},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-Z1-32B-0414 is a reasoning-focused AI model built on GLM-4-32B-0414. It has been enhanced through cold-start methods and reinforcement learning, with a strong emphasis on math, coding, and logic tasks. Despite having only 32B parameters, it performs comparably to the 671B DeepSeek-R1 on some benchmarks. It excels in complex reasoning tasks, as shown in evaluations like AIME 24/25, LiveCodeBench, and GPQA.","typeHints":["llm"],"pricing":{"input":0.08,"output":0.08},"source":"public-provider-conf"},"vision":false},{"id":"Pro/THUDM/GLM-4.1V-9B-Thinking","name":"Pro/THUDM/GLM-4.1V-9B-Thinking","display_name":"Pro/THUDM/GLM-4.1V-9B-Thinking","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.04,"output":0.16},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-4.1V-9B-Thinking is an open-source Vision Language Model (VLM) jointly released by Zhipu AI and the KEG Laboratory at Tsinghua University, designed specifically for handling complex multimodal cognitive tasks. Based on the GLM-4-9B-0414 foundation model, it significantly enhances cross-modal reasoning ability and stability by introducing the “Chain-of-Thought” reasoning mechanism and using reinforcement learning strategies. As a lightweight model with 9 billion parameters, it strikes a balance between deployment efficiency and performance. In 28 authoritative benchmark evaluations, it matched or even outperformed the 72-billion-parameter Qwen-2.5-VL-72B model in 18 tasks. The model excels not only in image-text understanding, mathematical and scientific reasoning, and video understanding, but also supports images up to 4K resolution and inputs of arbitrary aspect ratios.","typeHints":["llm"],"pricing":{"input":0.04,"output":0.16},"source":"public-provider-conf"},"vision":false},{"id":"THUDM/GLM-4.1V-9B-Thinking","name":"THUDM/GLM-4.1V-9B-Thinking","display_name":"THUDM/GLM-4.1V-9B-Thinking","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-4.1V-9B-Thinking is an open-source Vision Language Model (VLM) jointly released by Zhipu AI and the KEG Laboratory at Tsinghua University, designed specifically for handling complex multimodal cognitive tasks. Based on the GLM-4-9B-0414 foundation model, it significantly enhances cross-modal reasoning ability and stability by introducing the “Chain-of-Thought” reasoning mechanism and using reinforcement learning strategies. As a lightweight model with 9 billion parameters, it strikes a balance between deployment efficiency and performance. In 28 authoritative benchmark evaluations, it matched or even outperformed the 72-billion-parameter Qwen-2.5-VL-72B model in 18 tasks. The model excels not only in image-text understanding, mathematical and scientific reasoning, and video understanding, but also supports images up to 4K resolution and inputs of arbitrary aspect ratios.","typeHints":["llm"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"text-embedding-004","name":"text-embedding-004","display_name":"text-embedding-004","type":"embedding","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"THUDM/GLM-4-32B-0414","name":"THUDM/GLM-4-32B-0414","display_name":"THUDM/GLM-4-32B-0414","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.08,"output":0.08},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-4-32B-0414 is a next-generation open-source model with 32 billion parameters, delivering performance comparable to OpenAI’s GPT series and DeepSeek V3/R1. It supports smooth local deployment.\n\nThe base model was pre-trained on 15T of high-quality data, including a large amount of reasoning-focused synthetic content, setting the stage for advanced reinforcement learning.\n\nIn the post-training phase, techniques like human preference alignment, rejection sampling, and reinforcement learning were used to improve the model’s ability to follow instructions, generate code, and handle function calls—core skills needed for agent-style tasks.\n\nGLM-4-32B-0414 has shown strong results in engineering code, artifact generation, function calling, search-based QA, and report writing—sometimes matching or even surpassing larger models like GPT-4o and DeepSeek-V3 (671B) on specific benchmarks.","typeHints":["llm"],"pricing":{"input":0.08,"output":0.08},"source":"public-provider-conf"},"vision":false},{"id":"THUDM/GLM-Z1-9B-0414","name":"THUDM/GLM-Z1-9B-0414","display_name":"THUDM/GLM-Z1-9B-0414","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-Z1-9B-0414 is a small but powerful model in the GLM series, with only 9 billion parameters. Despite its size, it delivers strong performance in math reasoning and general tasks, ranking among the best in its class of open-source models.\n\nTrained with the same techniques as larger models, it strikes an excellent balance between performance and efficiency—making it a great option for low-resource or lightweight deployment scenarios.","typeHints":["llm"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"THUDM/GLM-4-9B-0414","name":"THUDM/GLM-4-9B-0414","display_name":"THUDM/GLM-4-9B-0414","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-4-9B-0414 is a lightweight model in the GLM family, with 9 billion parameters. It inherits the core tech from GLM-4-32B and offers an efficient option for deployment on limited resources.\n\nDespite its smaller size, it performs well in tasks like code generation, web design, SVG graphics creation, and search-based writing. It also supports function calling to interact with external tools, enhancing its versatility.\n\nGLM-4-9B-0414 strikes a solid balance between efficiency and performance, making it a strong choice for low-resource environments—while remaining competitive on various benchmarks.","typeHints":["llm"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"cc-doubao-seed-code-preview-latest","name":"cc-doubao-seed-code-preview-latest","display_name":"cc-doubao-seed-code-preview-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"claude code","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"doubao-seed-code-preview-latest","name":"doubao-seed-code-preview-latest","display_name":"doubao-seed-code-preview-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"chat","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/Janus-Pro-7B","name":"deepseek-ai/Janus-Pro-7B","display_name":"deepseek-ai/Janus-Pro-7B","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation","llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"glm-zero-preview","name":"glm-zero-preview","display_name":"glm-zero-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Simply put, it is the intelligent enhanced version of O1.","typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"qwen-3-235b-a22b-instruct-2507","name":"qwen-3-235b-a22b-instruct-2507","display_name":"qwen-3-235b-a22b-instruct-2507","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.28,"output":1.4},"limit":{"context":8192,"output":8192},"metadata":{"description":"cerebras","typeHints":["llm"],"pricing":{"input":0.28,"output":1.4},"source":"public-provider-conf"},"vision":false},{"id":"nvidia-llama-3.1-nemotron-70b-instruct","name":"nvidia-llama-3.1-nemotron-70b-instruct","display_name":"nvidia-llama-3.1-nemotron-70b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.32,"output":1.32},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.32,"output":1.32},"source":"public-provider-conf"},"vision":false},{"id":"nvidia-llama-3.3-nemotron-super-49b-v1.5","name":"nvidia-llama-3.3-nemotron-super-49b-v1.5","display_name":"nvidia-llama-3.3-nemotron-super-49b-v1.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.11,"output":0.44},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.11,"output":0.44},"source":"public-provider-conf"},"vision":false},{"id":"nvidia-nemotron-3-nano-30b-a3b","name":"nvidia-nemotron-3-nano-30b-a3b","display_name":"nvidia-nemotron-3-nano-30b-a3b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.066,"output":0.264},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.066,"output":0.264},"source":"public-provider-conf"},"vision":false},{"id":"nvidia-nemotron-nano-12b-v2-vl","name":"nvidia-nemotron-nano-12b-v2-vl","display_name":"nvidia-nemotron-nano-12b-v2-vl","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.22,"output":0.66},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.22,"output":0.66},"source":"public-provider-conf"},"vision":false},{"id":"nvidia-nemotron-nano-9b-v2","name":"nvidia-nemotron-nano-9b-v2","display_name":"nvidia-nemotron-nano-9b-v2","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.044,"output":0.176},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.044,"output":0.176},"source":"public-provider-conf"},"vision":false},{"id":"o1-preview-2024-09-12","name":"o1-preview-2024-09-12","display_name":"o1-preview-2024-09-12","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":15,"output":60,"cache_read":7.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":7.5,"input":15,"output":60},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"glm-4.5-air","name":"glm-4.5-air","display_name":"glm-4.5-air","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.14,"output":0.84},"limit":{"context":131072,"output":131072},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.14,"output":0.84},"source":"public-provider-conf"},"vision":false},{"id":"coding-glm-4.5-air","name":"coding-glm-4.5-air","display_name":"coding-glm-4.5-air","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.014,"output":0.084},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.014,"output":0.084},"source":"public-provider-conf"},"vision":false},{"id":"deepinfra-nvidia-nemotron-3-nano-30b-a3b2","name":"deepinfra-nvidia-nemotron-3-nano-30b-a3b2","display_name":"deepinfra-nvidia-nemotron-3-nano-30b-a3b2","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.066,"output":0.264},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.066,"output":0.264},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/QVQ-72B-Preview","name":"Qwen/QVQ-72B-Preview","display_name":"Qwen/QVQ-72B-Preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.2,"output":1.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.2,"output":1.2},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/QwQ-32B-Preview","name":"Qwen/QwQ-32B-Preview","display_name":"Qwen/QwQ-32B-Preview","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.16,"output":0.16},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.16},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"aihubmix-Mistral-Large-2411","name":"aihubmix-Mistral-Large-2411","display_name":"aihubmix-Mistral-Large-2411","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":6},"limit":{"context":8192,"output":8192},"metadata":{"description":"The latest Mistral Large 2 model is deployed on Azure.","typeHints":["llm"],"pricing":{"input":2,"output":6},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Mistral-large-2407","name":"aihubmix-Mistral-large-2407","display_name":"aihubmix-Mistral-large-2407","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":3,"output":9},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":3,"output":9},"source":"public-provider-conf"},"vision":false},{"id":"grok-2-1212","name":"grok-2-1212","display_name":"grok-2-1212","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.8,"output":9},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.8,"output":9},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.1-70b","name":"llama-3.1-70b","display_name":"llama-3.1-70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.44,"output":0.44},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.44,"output":0.44},"source":"public-provider-conf"},"vision":false},{"id":"wan2.6-t2i","name":"wan2.6-t2i","display_name":"wan2.6-t2i","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation"],"inputModalities":["image","text"],"source":"public-provider-conf"},"vision":true},{"id":"sf-kimi-k2-thinking","name":"sf-kimi-k2-thinking","display_name":"sf-kimi-k2-thinking","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.548,"output":2.192},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.548,"output":2.192},"source":"public-provider-conf"},"vision":false},{"id":"bai-qwen3-vl-235b-a22b-instruct","name":"bai-qwen3-vl-235b-a22b-instruct","display_name":"bai-qwen3-vl-235b-a22b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.274,"output":1.096},"limit":{"context":8192,"output":8192},"metadata":{"description":"The Qwen3 series open-source models include hybrid models, thinking models, and non-thinking models, with both reasoning capabilities and general abilities reaching industry SOTA levels at the same scale.","typeHints":["llm"],"pricing":{"input":0.274,"output":1.096},"source":"public-provider-conf"},"vision":false},{"id":"cc-MiniMax-M2","name":"cc-MiniMax-M2","display_name":"cc-MiniMax-M2","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude Code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"cc-deepseek-v3","name":"cc-deepseek-v3","display_name":"cc-deepseek-v3","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.3,"output":0.3},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude code only","typeHints":["llm"],"pricing":{"input":0.3,"output":0.3},"source":"public-provider-conf"},"vision":false},{"id":"cc-deepseek-v3.1","name":"cc-deepseek-v3.1","display_name":"cc-deepseek-v3.1","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.56,"output":1.68},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.56,"output":1.68},"source":"public-provider-conf"},"vision":false},{"id":"cc-ernie-4.5-300b-a47b","name":"cc-ernie-4.5-300b-a47b","display_name":"cc-ernie-4.5-300b-a47b","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":0.32,"output":1.28},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"input":0.32,"output":1.28},"source":"public-provider-conf"},"vision":true},{"id":"cc-kimi-dev-72b","name":"cc-kimi-dev-72b","display_name":"cc-kimi-dev-72b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.32,"output":1.28},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude code only","typeHints":["llm"],"pricing":{"input":0.32,"output":1.28},"source":"public-provider-conf"},"vision":false},{"id":"cc-kimi-k2-instruct","name":"cc-kimi-k2-instruct","display_name":"cc-kimi-k2-instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.1,"output":3.3},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":1.1,"output":3.3},"source":"public-provider-conf"},"vision":false},{"id":"cc-kimi-k2-instruct-0905","name":"cc-kimi-k2-instruct-0905","display_name":"cc-kimi-k2-instruct-0905","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":1.1,"output":3.3},"limit":{"context":8192,"output":8192},"metadata":{"description":"For Claude code only","typeHints":["llm"],"features":["tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":1.1,"output":3.3},"source":"public-provider-conf"},"vision":false},{"id":"cc-kimi-k2-thinking","name":"cc-kimi-k2-thinking","display_name":"cc-kimi-k2-thinking","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.548,"output":2.192},"limit":{"context":8192,"output":8192},"metadata":{"description":"Dedicated for Claude Code","typeHints":["llm"],"pricing":{"input":0.548,"output":2.192},"source":"public-provider-conf"},"vision":false},{"id":"computer-use-preview","name":"computer-use-preview","display_name":"computer-use-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":3,"output":12},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":3,"output":12},"source":"public-provider-conf"},"vision":false},{"id":"gpt-image-test","name":"gpt-image-test","display_name":"gpt-image-test","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"cost":{"input":5,"output":40},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation"],"pricing":{"input":5,"output":40},"source":"public-provider-conf"},"vision":false},{"id":"grok-4.20-beta-0309-non-reasoning","name":"grok-4.20-beta-0309-non-reasoning","display_name":"grok-4.20-beta-0309-non-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":2000000,"output":2000000},"metadata":{"description":"Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent tool-invocation capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, enabling it to consistently deliver precise and factual responses.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":2,"output":6},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.20-beta-0309-reasoning","name":"grok-4.20-beta-0309-reasoning","display_name":"grok-4.20-beta-0309-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":2000000,"output":2000000},"metadata":{"description":"Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent tool-invocation capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, enabling it to consistently deliver precise and factual responses.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":2,"output":6},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.20-multi-agent-beta-0309","name":"grok-4.20-multi-agent-beta-0309","display_name":"grok-4.20-multi-agent-beta-0309","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":2000000,"output":2000000},"metadata":{"description":"Grok 4.20 Beta is our latest flagship model, offering industry-leading speed and agent tool-invocation capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, enabling it to consistently deliver precise and factual responses.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs","long_context"],"inputModalities":["text","image"],"pricing":{"cache_read":0.2,"input":2,"output":6},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"jina-reader","name":"jina-reader","display_name":"jina-reader","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["search"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"jina-search","name":"jina-search","display_name":"jina-search","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["search"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"llama3.1-8b","name":"llama3.1-8b","display_name":"llama3.1-8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.3,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"description":"cerebras","typeHints":["llm"],"pricing":{"input":0.3,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"o1-2024-12-17","name":"o1-2024-12-17","display_name":"o1-2024-12-17","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":15,"output":60,"cache_read":7.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"features":["thinking"],"inputModalities":["text","image"],"pricing":{"cache_read":7.5,"input":15,"output":60},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-sol-pro","name":"gpt-5.6-sol-pro","display_name":"gpt-5.6-sol-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":8,"output":40,"cache_read":0.8},"limit":{"context":1050000,"output":1050000},"metadata":{"description":"gpt-5.6-sol-pro is OpenAI's multimodal model, designed for complex reasoning and generation tasks. It supports text and image inputs alongside an extensive 1,050,000-token context window. Compared with GPT-5.6 Sol, it is served with reasoning.mode set to pro for higher-quality responses on complex tasks.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.8,"input":8,"output":40},"source":"public-provider-conf"},"vision":true},{"id":"gpt-oss-20b","name":"gpt-oss-20b","display_name":"gpt-oss-20b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.11,"output":0.55},"limit":{"context":128000,"output":128000},"metadata":{"description":"gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the Apache 2.0 license. Its core feature is a Mixture-of-Experts (MoE) architecture that uses only 3.6B active parameters, enabling low-latency inference and deployment on consumer GPUs. The model also supports fine-tuning, function calling, tool use, and structured outputs.","typeHints":["llm"],"features":["thinking","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.11,"output":0.55},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-2-vision-1212","name":"grok-2-vision-1212","display_name":"grok-2-vision-1212","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":1.8,"output":9},"limit":{"context":8192,"output":8192},"metadata":{"description":"grok-2-vision-1212 is the latest vision model in the Grok family, delivering outstanding performance on vision-based tasks and achieving state-of-the-art results in visual mathematical reasoning and document-based question answering. It supports a wide range of visual inputs, including documents, charts, screenshots, and real-world images, making it well-suited for advanced visual understanding and reasoning use cases.\n\nThe price of calling this model in AIhubMix is ​​10% lower than on the official website.","typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":1.8,"output":9},"source":"public-provider-conf"},"vision":true},{"id":"grok-vision-beta","name":"grok-vision-beta","display_name":"grok-vision-beta","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":5.6,"output":16.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":5.6,"output":16.8},"source":"public-provider-conf"},"vision":true},{"id":"groq-llama-3.1-8b-instant","name":"groq-llama-3.1-8b-instant","display_name":"groq-llama-3.1-8b-instant","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.055,"output":0.088},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.055,"output":0.088},"source":"public-provider-conf"},"vision":false},{"id":"groq-llama-3.3-70b-versatile","name":"groq-llama-3.3-70b-versatile","display_name":"groq-llama-3.3-70b-versatile","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.649,"output":0.869011},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.649,"output":0.869011},"source":"public-provider-conf"},"vision":false},{"id":"groq-llama-4-maverick-17b-128e-instruct","name":"groq-llama-4-maverick-17b-128e-instruct","display_name":"groq-llama-4-maverick-17b-128e-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.22,"output":0.66},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.22,"output":0.66},"source":"public-provider-conf"},"vision":false},{"id":"groq-llama-4-scout-17b-16e-instruct","name":"groq-llama-4-scout-17b-16e-instruct","display_name":"groq-llama-4-scout-17b-16e-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.122,"output":0.366},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.122,"output":0.366},"source":"public-provider-conf"},"vision":false},{"id":"jina-embeddings-v2-base-code","name":"jina-embeddings-v2-base-code","display_name":"jina-embeddings-v2-base-code","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.05,"output":0.05},"limit":{"context":8192,"output":8192},"metadata":{"description":"Model optimized for code and document search, 768-dimensional, 137M parameters.","typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.05,"output":0.05},"source":"public-provider-conf"},"vision":false},{"id":"laguna-s-2.1","name":"laguna-s-2.1","display_name":"laguna-s-2.1","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"laguna-s-2.1 is Poolside's coding agent model, designed for programming and developer agent workflows. It offers a massive 1,048,576-token context window, a 118B total parameter architecture with 8B active parameters, and cost-effective text processing with prompt caching.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.01,"input":0.1,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"laguna-xs-2.1","name":"laguna-xs-2.1","display_name":"laguna-xs-2.1","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.2,"cache_read":0.05},"limit":{"context":262144,"output":262144},"metadata":{"description":"laguna-xs-2.1 is Poolside's coding agent model, designed for coding and text generation tasks. It features a 262,144-token context window with cost-effective pricing across input, output, and prompt caching. Compared with Laguna XS.2, it represents Poolside's latest step forward in the 33B-A3B category.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.05,"input":0.1,"output":0.2},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"learnlm-1.5-pro-experimental","name":"learnlm-1.5-pro-experimental","display_name":"learnlm-1.5-pro-experimental","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.25,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.25,"output":5},"source":"public-provider-conf"},"vision":false},{"id":"ling-3.0-flash","name":"ling-3.0-flash","display_name":"ling-3.0-flash","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"limit":{"context":262144,"output":262144},"metadata":{"description":"ling-3.0-flash is Inclusionai's 124B Mixture-of-Experts (MoE) text model, designed for production-scale agentic inference and token-efficient text generation. Activating approximately 5.1B parameters per token, it offers an extensive 262,144-token context window alongside cost-effective pricing at $0.06 per 1M input, $0.18 per 1M output, and $0.01 per 1M cache tokens.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.012,"input":0.06,"output":0.18},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"llama-3.1-405b-instruct","name":"llama-3.1-405b-instruct","display_name":"llama-3.1-405b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":4,"output":4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":4,"output":4},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.1-405b-reasoning","name":"llama-3.1-405b-reasoning","display_name":"llama-3.1-405b-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":4,"output":4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":4,"output":4},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.1-70b-versatile","name":"llama-3.1-70b-versatile","display_name":"llama-3.1-70b-versatile","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.6,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.6,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.1-8b-instant","name":"llama-3.1-8b-instant","display_name":"llama-3.1-8b-instant","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.3,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.3,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.2-11b-vision-preview","name":"llama-3.2-11b-vision-preview","display_name":"llama-3.2-11b-vision-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.2-1b-preview","name":"llama-3.2-1b-preview","display_name":"llama-3.2-1b-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.2-3b-preview","name":"llama-3.2-3b-preview","display_name":"llama-3.2-3b-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.2-90b-vision-preview","name":"llama-3.2-90b-vision-preview","display_name":"llama-3.2-90b-vision-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.4,"output":2.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2.4,"output":2.4},"source":"public-provider-conf"},"vision":false},{"id":"llama-3.3-70b-instruct","name":"llama-3.3-70b-instruct","display_name":"llama-3.3-70b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.6,"output":1.2},"limit":{"context":131072,"output":131072},"metadata":{"typeHints":["llm"],"features":["long_context"],"inputModalities":["text"],"pricing":{"input":0.6,"output":1.2},"source":"public-provider-conf"},"vision":false},{"id":"llama2-70b-4096","name":"llama2-70b-4096","display_name":"llama2-70b-4096","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":false},{"id":"llama2-70b-40960","name":"llama2-70b-40960","display_name":"llama2-70b-40960","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":false},{"id":"llama2-7b-2048","name":"llama2-7b-2048","display_name":"llama2-7b-2048","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"llama3-70b-8192","name":"llama3-70b-8192","display_name":"llama3-70b-8192","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.7,"output":0.937288},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.7,"output":0.937288},"source":"public-provider-conf"},"vision":false},{"id":"llama3-70b-8192(33)","name":"llama3-70b-8192(33)","display_name":"llama3-70b-8192(33)","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.65,"output":2.65},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2.65,"output":2.65},"source":"public-provider-conf"},"vision":false},{"id":"llama3-8b-8192","name":"llama3-8b-8192","display_name":"llama3-8b-8192","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.06,"output":0.12},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.06,"output":0.12},"source":"public-provider-conf"},"vision":false},{"id":"llama3-8b-8192(33)","name":"llama3-8b-8192(33)","display_name":"llama3-8b-8192(33)","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.3,"output":0.3},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.3,"output":0.3},"source":"public-provider-conf"},"vision":false},{"id":"llama3-groq-70b-8192-tool-use-preview","name":"llama3-groq-70b-8192-tool-use-preview","display_name":"llama3-groq-70b-8192-tool-use-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.00089,"output":0.00089},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.00089,"output":0.00089},"source":"public-provider-conf"},"vision":false},{"id":"llama3-groq-8b-8192-tool-use-preview","name":"llama3-groq-8b-8192-tool-use-preview","display_name":"llama3-groq-8b-8192-tool-use-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.00019,"output":0.00019},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.00019,"output":0.00019},"source":"public-provider-conf"},"vision":false},{"id":"mercury-2.5","name":"mercury-2.5","display_name":"mercury-2.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.75,"cache_read":0.02},"limit":{"context":260000,"output":260000},"metadata":{"description":"Mercury 2.5 is Inception's diffusion language model (dLLM), designed for text generation and reasoning tasks. Instead of sequential generation, it produces and refines multiple tokens in parallel to achieve rapid reasoning, supported by an expansive 260,000-token context window.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.02,"input":0.2,"output":0.75},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/Llama-3.2-90B-Vision-Instruct","name":"meta-llama/Llama-3.2-90B-Vision-Instruct","display_name":"meta-llama/Llama-3.2-90B-Vision-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.1-405b-instruct:free","name":"meta-llama/llama-3.1-405b-instruct:free","display_name":"meta-llama/llama-3.1-405b-instruct:free","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.1-70b-instruct:free","name":"meta-llama/llama-3.1-70b-instruct:free","display_name":"meta-llama/llama-3.1-70b-instruct:free","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.1-8b-instruct:free","name":"meta-llama/llama-3.1-8b-instruct:free","display_name":"meta-llama/llama-3.1-8b-instruct:free","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.2-11b-vision-instruct:free","name":"meta-llama/llama-3.2-11b-vision-instruct:free","display_name":"meta-llama/llama-3.2-11b-vision-instruct:free","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.2-3b-instruct:free","name":"meta-llama/llama-3.2-3b-instruct:free","display_name":"meta-llama/llama-3.2-3b-instruct:free","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"meta/llama-3.1-405b-instruct","name":"meta/llama-3.1-405b-instruct","display_name":"meta/llama-3.1-405b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":5,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":5,"output":5},"source":"public-provider-conf"},"vision":false},{"id":"meta/llama3-8B-chat","name":"meta/llama3-8B-chat","display_name":"meta/llama3-8B-chat","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.3,"output":0.3},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.3,"output":0.3},"source":"public-provider-conf"},"vision":false},{"id":"mistralai/mistral-7b-instruct:free","name":"mistralai/mistral-7b-instruct:free","display_name":"mistralai/mistral-7b-instruct:free","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.002,"output":0.002},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.002,"output":0.002},"source":"public-provider-conf"},"vision":false},{"id":"moonshot-v1-128k","name":"moonshot-v1-128k","display_name":"moonshot-v1-128k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":10,"output":10},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":10,"output":10},"source":"public-provider-conf"},"vision":false},{"id":"moonshot-v1-128k-vision-preview","name":"moonshot-v1-128k-vision-preview","display_name":"moonshot-v1-128k-vision-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":10,"output":10},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":10,"output":10},"source":"public-provider-conf"},"vision":false},{"id":"moonshot-v1-32k","name":"moonshot-v1-32k","display_name":"moonshot-v1-32k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":4,"output":4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":4,"output":4},"source":"public-provider-conf"},"vision":false},{"id":"moonshot-v1-32k-vision-preview","name":"moonshot-v1-32k-vision-preview","display_name":"moonshot-v1-32k-vision-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":4,"output":4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":4,"output":4},"source":"public-provider-conf"},"vision":false},{"id":"moonshot-v1-8k","name":"moonshot-v1-8k","display_name":"moonshot-v1-8k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"moonshot-v1-8k-vision-preview","name":"moonshot-v1-8k-vision-preview","display_name":"moonshot-v1-8k-vision-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","name":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","display_name":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Llama-3.1-Nemotron-Ultra-253B is a 253 billion parameter reasoning-focused language model optimized for efficiency that excels at math, coding, and general instruction-following tasks while running on a single 8xH100 node.","typeHints":["llm"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":false},{"id":"o1-mini-2024-09-12","name":"o1-mini-2024-09-12","display_name":"o1-mini-2024-09-12","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":3,"output":12,"cache_read":1.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":1.5,"input":3,"output":12},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"omni-moderation-latest","name":"omni-moderation-latest","display_name":"omni-moderation-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["moderation"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"qwen-flash","name":"qwen-flash","display_name":"qwen-flash","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.02,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"The model adopts tiered pricing.","typeHints":["llm"],"pricing":{"input":0.02,"output":0.2,"tiers":[{"input":0.082192,"output":0.82192,"tier":{"size":128000,"type":"context"}},{"input":0.164382,"output":1.64382,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-flash-2025-07-28","name":"qwen-flash-2025-07-28","display_name":"qwen-flash-2025-07-28","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.02,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"The model adopts tiered pricing.","typeHints":["llm"],"pricing":{"input":0.02,"output":0.2,"tiers":[{"input":0.08219,"output":0.8219,"tier":{"size":128000,"type":"context"}},{"input":0.164382,"output":1.64382,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-long","name":"qwen-long","display_name":"qwen-long","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.1,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"qwen-max","name":"qwen-max","display_name":"qwen-max","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.38,"output":1.52},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.38,"output":1.52},"source":"public-provider-conf"},"vision":false},{"id":"qwen-max-longcontext","name":"qwen-max-longcontext","display_name":"qwen-max-longcontext","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":7,"output":21},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":7,"output":21},"source":"public-provider-conf"},"vision":false},{"id":"qwen-plus","name":"qwen-plus","display_name":"qwen-plus","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.1126,"output":1.126,"cache_read":0.02252},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.02252,"cache_write":0.14075,"input":0.1126,"output":1.126,"tiers":[{"cache_read":0.0676,"cache_write":0.4225,"input":0.338,"output":3.38,"tier":{"size":128000,"type":"context"}},{"cache_read":0.1352,"cache_write":0.845,"input":0.676,"output":9.013311,"tier":{"size":256000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-turbo","name":"qwen-turbo","display_name":"qwen-turbo","type":"chat","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.046,"output":0.092,"cache_read":0.0092},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"features":["long_context"],"inputModalities":["text"],"pricing":{"cache_read":0.0092,"input":0.046,"output":0.092},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen-turbo-2024-11-01","name":"qwen-turbo-2024-11-01","display_name":"qwen-turbo-2024-11-01","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.046,"output":0.092},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"features":["long_context"],"inputModalities":["text"],"pricing":{"input":0.046,"output":0.092},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-14b-instruct","name":"qwen2.5-14b-instruct","display_name":"qwen2.5-14b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":1.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":1.2},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-32b-instruct","name":"qwen2.5-32b-instruct","display_name":"qwen2.5-32b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.6,"output":1.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.6,"output":1.2},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-3b-instruct","name":"qwen2.5-3b-instruct","display_name":"qwen2.5-3b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-72b-instruct","name":"qwen2.5-72b-instruct","display_name":"qwen2.5-72b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":2.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":2.4},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-7b-instruct","name":"qwen2.5-7b-instruct","display_name":"qwen2.5-7b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-coder-1.5b-instruct","name":"qwen2.5-coder-1.5b-instruct","display_name":"qwen2.5-coder-1.5b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-coder-7b-instruct","name":"qwen2.5-coder-7b-instruct","display_name":"qwen2.5-coder-7b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-math-1.5b-instruct","name":"qwen2.5-math-1.5b-instruct","display_name":"qwen2.5-math-1.5b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-math-72b-instruct","name":"qwen2.5-math-72b-instruct","display_name":"qwen2.5-math-72b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":2.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":2.4},"source":"public-provider-conf"},"vision":false},{"id":"qwen2.5-math-7b-instruct","name":"qwen2.5-math-7b-instruct","display_name":"qwen2.5-math-7b-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"qwen3-235b-a22b-2507","name":"qwen3-235b-a22b-2507","display_name":"qwen3-235b-a22b-2507","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.35,"output":1.4,"cache_read":0.07},"limit":{"context":262144,"output":262144},"metadata":{"description":"qwen3-235b-a22b-2507 is Qwen's multilingual, instruction-tuned mixture-of-experts language model, designed for general-purpose text generation and instruction following. Built on the Qwen3-235B architecture, it utilizes 22B active parameters per forward pass and features an extensive context window of 262,144 tokens.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.07,"input":0.35,"output":1.4},"source":"public-provider-conf"},"vision":false},{"id":"qwen3.8-27b","name":"qwen3.8-27b","display_name":"qwen3.8-27b","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"]},"cost":{"input":0.2,"output":2.5,"cache_read":0.05},"limit":{"context":1000000,"output":1000000},"metadata":{"description":"qwen3.8-27b is Qwen's open-weight dense vision-language model, designed for coding, professional workflows, research, multimodal interaction, and long-running agent tasks. It supports text and image inputs with an extensive 1,000,000-token context length and flexible thinking capabilities.","typeHints":["llm"],"inputModalities":["text","image","video"],"pricing":{"cache_read":0.05,"input":0.2,"output":2.5},"source":"public-provider-conf"},"vision":true},{"id":"solar-pro4","name":"solar-pro4","display_name":"solar-pro4","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"limit":{"context":524288,"output":524288},"metadata":{"typeHints":["llm"],"features":["long_context"],"inputModalities":["text"],"pricing":{"cache_read":0.06,"input":0.3,"output":1.2},"source":"public-provider-conf"},"vision":false},{"id":"step-2-16k","name":"step-2-16k","display_name":"step-2-16k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"text-ada-001","name":"text-ada-001","display_name":"text-ada-001","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"text-babbage-001","name":"text-babbage-001","display_name":"text-babbage-001","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.5,"output":0.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.5,"output":0.5},"source":"public-provider-conf"},"vision":false},{"id":"text-curie-001","name":"text-curie-001","display_name":"text-curie-001","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"text-davinci-002","name":"text-davinci-002","display_name":"text-davinci-002","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":20,"output":20},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":20,"output":20},"source":"public-provider-conf"},"vision":false},{"id":"text-davinci-003","name":"text-davinci-003","display_name":"text-davinci-003","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":20,"output":20},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":20,"output":20},"source":"public-provider-conf"},"vision":false},{"id":"text-davinci-edit-001","name":"text-davinci-edit-001","display_name":"text-davinci-edit-001","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":20,"output":20},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":20,"output":20},"source":"public-provider-conf"},"vision":false},{"id":"text-embedding-3-large","name":"text-embedding-3-large","display_name":"text-embedding-3-large","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.13,"output":0.13},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.13,"output":0.13},"source":"public-provider-conf"},"vision":false},{"id":"text-embedding-3-small","name":"text-embedding-3-small","display_name":"text-embedding-3-small","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"text-embedding-ada-002","name":"text-embedding-ada-002","display_name":"text-embedding-ada-002","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"text-embedding-v1","name":"text-embedding-v1","display_name":"text-embedding-v1","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"text-moderation-007","name":"text-moderation-007","display_name":"text-moderation-007","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["moderation"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"text-moderation-latest","name":"text-moderation-latest","display_name":"text-moderation-latest","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["moderation"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"text-moderation-stable","name":"text-moderation-stable","display_name":"text-moderation-stable","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["moderation"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"text-search-ada-doc-001","name":"text-search-ada-doc-001","display_name":"text-search-ada-doc-001","type":"embedding","reasoning":{"supported":false},"tool_call":false,"cost":{"input":20,"output":20},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"pricing":{"input":20,"output":20},"source":"public-provider-conf"},"vision":false},{"id":"tts-1","name":"tts-1","display_name":"tts-1","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["tts"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"tts-1-1106","name":"tts-1-1106","display_name":"tts-1-1106","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["tts"],"inputModalities":["audio"],"source":"public-provider-conf"},"vision":false},{"id":"tts-1-hd","name":"tts-1-hd","display_name":"tts-1-hd","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["tts"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"tts-1-hd-1106","name":"tts-1-hd-1106","display_name":"tts-1-hd-1106","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["tts"],"inputModalities":["audio"],"source":"public-provider-conf"},"vision":false},{"id":"whisper-1","name":"whisper-1","display_name":"whisper-1","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Ignore the displayed price on the page; the actual charge for this model request is consistent with the official, so you can use it with confidence.","typeHints":["stt"],"inputModalities":["audio"],"source":"public-provider-conf"},"vision":false},{"id":"whisper-large-v3","name":"whisper-large-v3","display_name":"whisper-large-v3","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["stt"],"inputModalities":["audio"],"source":"public-provider-conf"},"vision":false},{"id":"whisper-large-v3-turbo","name":"whisper-large-v3-turbo","display_name":"whisper-large-v3-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["stt"],"inputModalities":["audio"],"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","name":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.6,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.6,"output":0.6},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","name":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.01,"output":0.01},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.01,"output":0.01},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.01,"output":0.01},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.01,"output":0.01},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"description":"Open source deployment from SiliconFlow, the model itself is obtained through knowledge distillation.","typeHints":["llm"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Open source deployment from SiliconFlow, the model itself is obtained through knowledge distillation.","typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","display_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.01,"output":0.01},"limit":{"context":8192,"output":8192},"metadata":{"description":"Open source deployment from SiliconFlow, the model itself is obtained through knowledge distillation.","typeHints":["llm"],"pricing":{"input":0.01,"output":0.01},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-V2-Chat","name":"deepseek-ai/DeepSeek-V2-Chat","display_name":"deepseek-ai/DeepSeek-V2-Chat","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.16,"output":0.32},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.32},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-V2.5","name":"deepseek-ai/DeepSeek-V2.5","display_name":"deepseek-ai/DeepSeek-V2.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.16,"output":0.32},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.32},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/deepseek-llm-67b-chat","name":"deepseek-ai/deepseek-llm-67b-chat","display_name":"deepseek-ai/deepseek-llm-67b-chat","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.16,"output":0.16},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.16},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/deepseek-vl2","name":"deepseek-ai/deepseek-vl2","display_name":"deepseek-ai/deepseek-vl2","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.16,"output":0.16},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.16},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-v3","name":"deepseek-v3","display_name":"deepseek-v3","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.272,"output":1.088},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.272,"output":1.088},"source":"public-provider-conf"},"vision":false},{"id":"distil-whisper-large-v3-en","name":"distil-whisper-large-v3-en","display_name":"distil-whisper-large-v3-en","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"]},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["stt"],"inputModalities":["audio"],"source":"public-provider-conf"},"vision":false},{"id":"doubao-1-5-thinking-vision-pro-250428","name":"doubao-1-5-thinking-vision-pro-250428","display_name":"doubao-1-5-thinking-vision-pro-250428","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"description":"Deep Thinking  \nImage Understanding  \nVisual Localization  \nVideo Understanding  \nTool Invocation  \nStructured Output","typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"fx-flux-2-pro","name":"fx-flux-2-pro","display_name":"fx-flux-2-pro","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation"],"source":"public-provider-conf"},"vision":false},{"id":"gemini-2.5-pro-exp-03-25","name":"gemini-2.5-pro-exp-03-25","display_name":"gemini-2.5-pro-exp-03-25","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","audio","video"]},"cost":{"input":1.25,"output":5,"cache_read":0.125},"limit":{"context":8192,"output":8192},"metadata":{"description":"Google’s latest experimental model, highly unstable, for experience only.\nIt boasts strong reasoning and coding capabilities, able to \"think\" before responding, enhancing performance and accuracy in complex tasks. It supports multimodal inputs (text, audio, images, video) and a 1 million token context window, suitable for advanced programming, math, and science tasks.\n\nThis means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.","typeHints":["llm"],"features":["structured_outputs","tools","long_context"],"inputModalities":["text","image","audio","video"],"pricing":{"cache_read":0.125,"input":1.25,"output":5,"tiers":[{"cache_read":0.25,"input":2.5,"output":15,"tier":{"size":200000,"type":"context"}}]},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-embedding-exp-03-07","name":"gemini-embedding-exp-03-07","display_name":"gemini-embedding-exp-03-07","type":"embedding","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.02,"output":0.02},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["embedding"],"inputModalities":["text"],"pricing":{"input":0.02,"output":0.02},"source":"public-provider-conf"},"vision":false},{"id":"gemini-exp-1114","name":"gemini-exp-1114","display_name":"gemini-exp-1114","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.25,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.25,"output":5},"source":"public-provider-conf"},"vision":false},{"id":"gemini-exp-1121","name":"gemini-exp-1121","display_name":"gemini-exp-1121","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.25,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.25,"output":5},"source":"public-provider-conf"},"vision":false},{"id":"gemini-pro","name":"gemini-pro","display_name":"gemini-pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"gemini-pro-vision","name":"gemini-pro-vision","display_name":"gemini-pro-vision","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":1},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1,"output":1},"source":"public-provider-conf"},"vision":false},{"id":"gemma-7b-it","name":"gemma-7b-it","display_name":"gemma-7b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"glm-3-turbo","name":"glm-3-turbo","display_name":"glm-3-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.71,"output":0.71},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.71,"output":0.71},"source":"public-provider-conf"},"vision":false},{"id":"glm-4","name":"glm-4","display_name":"glm-4","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":14.2,"output":14.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":14.2,"output":14.2},"source":"public-provider-conf"},"vision":false},{"id":"glm-4-flash","name":"glm-4-flash","display_name":"glm-4-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.1,"output":0.1},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.1,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"glm-4-plus","name":"glm-4-plus","display_name":"glm-4-plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":8,"output":8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":8,"output":8},"source":"public-provider-conf"},"vision":false},{"id":"glm-4.5-airx","name":"glm-4.5-airx","display_name":"glm-4.5-airx","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":1.1,"output":4.51,"cache_read":0.22},"limit":{"context":8192,"output":8192},"metadata":{"description":"GLM-4.5-AirX is the high-speed version of GLM-4.5-Air, with faster response times, specifically designed for large-scale high-speed demands.","typeHints":["llm"],"inputModalities":["text"],"pricing":{"cache_read":0.22,"input":1.1,"output":4.51},"source":"public-provider-conf"},"vision":false},{"id":"glm-4v","name":"glm-4v","display_name":"glm-4v","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":14.2,"output":14.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":14.2,"output":14.2},"source":"public-provider-conf"},"vision":false},{"id":"glm-4v-plus","name":"glm-4v-plus","display_name":"glm-4v-plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"google-gemma-3-12b-it","name":"google-gemma-3-12b-it","display_name":"google-gemma-3-12b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"google-gemma-3-27b-it","name":"google-gemma-3-27b-it","display_name":"google-gemma-3-27b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"google-gemma-3-4b-it","name":"google-gemma-3-4b-it","display_name":"google-gemma-3-4b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"google/gemini-exp-1114","name":"google/gemini-exp-1114","display_name":"google/gemini-exp-1114","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.25,"output":5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.25,"output":5},"source":"public-provider-conf"},"vision":false},{"id":"google/gemma-2-27b-it","name":"google/gemma-2-27b-it","display_name":"google/gemma-2-27b-it","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"gpt-3.5-turbo","name":"gpt-3.5-turbo","display_name":"gpt-3.5-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.5,"output":1.5},"limit":{"context":8192,"output":8192},"metadata":{"description":"Since the GPT-3.5-turbo model has been officially deprecated, all requests targeting this model will be automatically routed to GPT-40-mini. We recommend using GPT-40-mini directly as a replacement.","typeHints":["llm"],"pricing":{"input":0.5,"output":1.5},"source":"public-provider-conf"},"vision":false},{"id":"gpt-3.5-turbo-1106","name":"gpt-3.5-turbo-1106","display_name":"gpt-3.5-turbo-1106","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"gpt-3.5-turbo-16k","name":"gpt-3.5-turbo-16k","display_name":"gpt-3.5-turbo-16k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":3,"output":4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":3,"output":4},"source":"public-provider-conf"},"vision":false},{"id":"gpt-3.5-turbo-instruct","name":"gpt-3.5-turbo-instruct","display_name":"gpt-3.5-turbo-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.5,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.5,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4","name":"gpt-4","display_name":"gpt-4","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":30,"output":60},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":30,"output":60},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4-0613","name":"gpt-4-0613","display_name":"gpt-4-0613","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":30,"output":60},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":30,"output":60},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4-1106-preview","name":"gpt-4-1106-preview","display_name":"gpt-4-1106-preview","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":10,"output":30},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":10,"output":30},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4-turbo","name":"gpt-4-turbo","display_name":"gpt-4-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":10,"output":30},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":10,"output":30},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4-turbo-2024-04-09","name":"gpt-4-turbo-2024-04-09","display_name":"gpt-4-turbo-2024-04-09","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":10,"output":30},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":10,"output":30},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4o-2024-05-13","name":"gpt-4o-2024-05-13","display_name":"gpt-4o-2024-05-13","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":5,"output":15,"cache_read":5},"limit":{"context":128000,"output":128000},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":5,"input":5,"output":15},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4o-mini-2024-07-18","name":"gpt-4o-mini-2024-07-18","display_name":"gpt-4o-mini-2024-07-18","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"source":"public-provider-conf"},"vision":true},{"id":"DeepSeek-v3","name":"DeepSeek-v3","display_name":"DeepSeek-v3","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.272,"output":1.088},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.272,"output":1.088},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-1.5-lite-32k","name":"Doubao-1.5-lite-32k","display_name":"Doubao-1.5-lite-32k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.05,"output":0.1,"cache_read":0.01},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-1.5-lite, a brand-new generation of lightweight model, offers exceptional response speed with both performance and latency reaching world-class levels. It supports a 32k context window and an output length of up to 12k tokens.","typeHints":["llm"],"pricing":{"cache_read":0.01,"input":0.05,"output":0.1},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-1.5-pro-256k","name":"Doubao-1.5-pro-256k","display_name":"Doubao-1.5-pro-256k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":1.44},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-1.5-pro-256k, a fully upgraded version based on Doubao-1.5-Pro, delivers an overall performance improvement of 10%. It supports inference with a 256k context window and an output length of up to 12k tokens. With higher performance, larger window size, and exceptional cost-effectiveness, it is suitable for a wider range of application scenarios.","typeHints":["llm"],"pricing":{"input":0.8,"output":1.44},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-1.5-pro-32k","name":"Doubao-1.5-pro-32k","display_name":"Doubao-1.5-pro-32k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.134,"output":0.335,"cache_read":0.0268},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-1.5-pro, a brand-new generation of flagship model, features comprehensive performance upgrades and excels in knowledge, coding, reasoning, and other aspects. It supports a 32k context window and an output length of up to 12k tokens.","typeHints":["llm"],"pricing":{"cache_read":0.0268,"input":0.134,"output":0.335},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-1.5-vision-pro-32k","name":"Doubao-1.5-vision-pro-32k","display_name":"Doubao-1.5-vision-pro-32k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.46,"output":1.38},"limit":{"context":8192,"output":8192},"metadata":{"description":"Doubao-1.5-vision-pro is a newly upgraded multimodal large model that supports image recognition at any resolution and extreme aspect ratios. It enhances visual reasoning, document recognition, detailed information understanding, and instruction-following capabilities. It supports a 32k context window and an output length of up to 12k tokens.","typeHints":["llm"],"pricing":{"input":0.46,"output":1.38},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-lite-128k","name":"Doubao-lite-128k","display_name":"Doubao-lite-128k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.14,"output":0.28},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.14,"output":0.28},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-lite-32k","name":"Doubao-lite-32k","display_name":"Doubao-lite-32k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.06,"output":0.12,"cache_read":0.012},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.012,"input":0.06,"output":0.12},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-lite-4k","name":"Doubao-lite-4k","display_name":"Doubao-lite-4k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.06,"output":0.12},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.06,"output":0.12},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-pro-128k","name":"Doubao-pro-128k","display_name":"Doubao-pro-128k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":1.44},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":1.44},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-pro-256k","name":"Doubao-pro-256k","display_name":"Doubao-pro-256k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":1.44},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":1.44},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-pro-32k","name":"Doubao-pro-32k","display_name":"Doubao-pro-32k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.14,"output":0.35,"cache_read":0.028},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.028,"input":0.14,"output":0.35},"source":"public-provider-conf"},"vision":false},{"id":"Doubao-pro-4k","name":"Doubao-pro-4k","display_name":"Doubao-pro-4k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.14,"output":0.35},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.14,"output":0.35},"source":"public-provider-conf"},"vision":false},{"id":"GPT-OSS-20B","name":"GPT-OSS-20B","display_name":"GPT-OSS-20B","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.11,"output":0.55},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.11,"output":0.55},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"Gryphe/MythoMax-L2-13b","name":"Gryphe/MythoMax-L2-13b","display_name":"Gryphe/MythoMax-L2-13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"MiniMax-Text-01","name":"MiniMax-Text-01","display_name":"MiniMax-Text-01","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.14,"output":1.12},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"features":["long_context"],"inputModalities":["text"],"pricing":{"input":0.14,"output":1.12},"source":"public-provider-conf"},"vision":false},{"id":"Mistral-large-2407","name":"Mistral-large-2407","display_name":"Mistral-large-2407","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":3,"output":9},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":3,"output":9},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2-1.5B-Instruct","name":"Qwen/Qwen2-1.5B-Instruct","display_name":"Qwen/Qwen2-1.5B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2,"output":0.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2,"output":0.2},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2-57B-A14B-Instruct","name":"Qwen/Qwen2-57B-A14B-Instruct","display_name":"Qwen/Qwen2-57B-A14B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.24,"output":0.24},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.24,"output":0.24},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2-72B-Instruct","name":"Qwen/Qwen2-72B-Instruct","display_name":"Qwen/Qwen2-72B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2-7B-Instruct","name":"Qwen/Qwen2-7B-Instruct","display_name":"Qwen/Qwen2-7B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.08,"output":0.08},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.08,"output":0.08},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2.5-32B-Instruct","name":"Qwen/Qwen2.5-32B-Instruct","display_name":"Qwen/Qwen2.5-32B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.6,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.6,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen/Qwen2.5-72B-Instruct","display_name":"Qwen/Qwen2.5-72B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2.5-72B-Instruct-128K","name":"Qwen/Qwen2.5-72B-Instruct-128K","display_name":"Qwen/Qwen2.5-72B-Instruct-128K","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.8,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.8,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen/Qwen2.5-7B-Instruct","display_name":"Qwen/Qwen2.5-7B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen/Qwen2.5-Coder-32B-Instruct","display_name":"Qwen/Qwen2.5-Coder-32B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.16,"output":0.16},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.16},"source":"public-provider-conf"},"vision":false},{"id":"Qwen3-235B-A22B-Thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","display_name":"Qwen3-235B-A22B-Thinking-2507","type":"chat","reasoning":{"supported":true},"tool_call":false,"cost":{"input":0.28,"output":2.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.28,"output":2.8},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"WizardLM/WizardCoder-Python-34B-V1.0","name":"WizardLM/WizardCoder-Python-34B-V1.0","display_name":"WizardLM/WizardCoder-Python-34B-V1.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.9,"output":0.9},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.9,"output":0.9},"source":"public-provider-conf"},"vision":false},{"id":"ahm-Phi-3-5-MoE-instruct","name":"ahm-Phi-3-5-MoE-instruct","display_name":"ahm-Phi-3-5-MoE-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":1.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":1.6},"source":"public-provider-conf"},"vision":false},{"id":"ahm-Phi-3-5-mini-instruct","name":"ahm-Phi-3-5-mini-instruct","display_name":"ahm-Phi-3-5-mini-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":3},"limit":{"context":8192,"output":8192},"metadata":{"description":"Phi-3.5-mini is a lightweight, state-of-the-art open model built upon the dataset used for Phi-3—which includes synthetic data and carefully curated publicly available websites—focusing on very high-quality, reasoning-intensive data. This model is part of the Phi-3 model family and supports a context length of 128K tokens.","typeHints":["llm"],"pricing":{"input":1,"output":3},"source":"public-provider-conf"},"vision":false},{"id":"ahm-Phi-3-5-vision-instruct","name":"ahm-Phi-3-5-vision-instruct","display_name":"ahm-Phi-3-5-vision-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.4,"output":1.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0.4,"output":1.6},"source":"public-provider-conf"},"vision":true},{"id":"ahm-Phi-3-medium-128k","name":"ahm-Phi-3-medium-128k","display_name":"ahm-Phi-3-medium-128k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":6,"output":18},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":6,"output":18},"source":"public-provider-conf"},"vision":false},{"id":"ahm-Phi-3-medium-4k","name":"ahm-Phi-3-medium-4k","display_name":"ahm-Phi-3-medium-4k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":3},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1,"output":3},"source":"public-provider-conf"},"vision":false},{"id":"ahm-Phi-3-small-128k","name":"ahm-Phi-3-small-128k","display_name":"ahm-Phi-3-small-128k","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":3},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1,"output":3},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Codestral-2501","name":"aihubmix-Codestral-2501","display_name":"aihubmix-Codestral-2501","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":1.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":1.2},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Cohere-command-r","name":"aihubmix-Cohere-command-r","display_name":"aihubmix-Cohere-command-r","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.64,"output":1.92},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.64,"output":1.92},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Jamba-1-5-Large","name":"aihubmix-Jamba-1-5-Large","display_name":"aihubmix-Jamba-1-5-Large","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.2,"output":8.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2.2,"output":8.8},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Llama-3-1-405B-Instruct","name":"aihubmix-Llama-3-1-405B-Instruct","display_name":"aihubmix-Llama-3-1-405B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":5,"output":15},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":5,"output":15},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Llama-3-1-70B-Instruct","name":"aihubmix-Llama-3-1-70B-Instruct","display_name":"aihubmix-Llama-3-1-70B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.6,"output":0.78},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.6,"output":0.78},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Llama-3-1-8B-Instruct","name":"aihubmix-Llama-3-1-8B-Instruct","display_name":"aihubmix-Llama-3-1-8B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.3,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.3,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Llama-3-2-11B-Vision","name":"aihubmix-Llama-3-2-11B-Vision","display_name":"aihubmix-Llama-3-2-11B-Vision","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.4,"output":0.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.4,"output":0.4},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Llama-3-2-90B-Vision","name":"aihubmix-Llama-3-2-90B-Vision","display_name":"aihubmix-Llama-3-2-90B-Vision","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.4,"output":2.4},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2.4,"output":2.4},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Llama-3-70B-Instruct","name":"aihubmix-Llama-3-70B-Instruct","display_name":"aihubmix-Llama-3-70B-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.7,"output":0.7},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.7,"output":0.7},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-Mistral-large","name":"aihubmix-Mistral-large","display_name":"aihubmix-Mistral-large","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":4,"output":12},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":4,"output":12},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-command-r-08-2024","name":"aihubmix-command-r-08-2024","display_name":"aihubmix-command-r-08-2024","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-command-r-plus","name":"aihubmix-command-r-plus","display_name":"aihubmix-command-r-plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":3.84,"output":19.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":3.84,"output":19.2},"source":"public-provider-conf"},"vision":false},{"id":"aihubmix-command-r-plus-08-2024","name":"aihubmix-command-r-plus-08-2024","display_name":"aihubmix-command-r-plus-08-2024","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":2.8,"output":11.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":2.8,"output":11.2},"source":"public-provider-conf"},"vision":false},{"id":"alicloud-deepseek-v3.2","name":"alicloud-deepseek-v3.2","display_name":"alicloud-deepseek-v3.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.274,"output":0.411,"cache_read":0.0548},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.0548,"cache_write":0.3425,"input":0.274,"output":0.411},"source":"public-provider-conf"},"vision":false},{"id":"alicloud-glm-4.7","name":"alicloud-glm-4.7","display_name":"alicloud-glm-4.7","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.41096,"output":1.917786,"cache_read":0.41096},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.41096,"input":0.41096,"output":1.917786,"tiers":[{"cache_read":0.547946,"input":0.547946,"output":2.191784,"tier":{"size":32000,"type":"context"}}]},"source":"public-provider-conf"},"vision":false},{"id":"alicloud-kimi-k2-thinking","name":"alicloud-kimi-k2-thinking","display_name":"alicloud-kimi-k2-thinking","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.548,"output":2.192},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.548,"output":2.192},"source":"public-provider-conf"},"vision":false},{"id":"alicloud-minimax-m2.5","name":"alicloud-minimax-m2.5","display_name":"alicloud-minimax-m2.5","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2876,"output":1.1504,"cache_read":0.05752},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.05752,"input":0.2876,"output":1.1504},"source":"public-provider-conf"},"vision":false},{"id":"anthropic-opus-4-6","name":"anthropic-opus-4-6","display_name":"anthropic-opus-4-6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"]},"cost":{"input":5,"output":25,"cache_read":0.5},"limit":{"context":200000,"output":200000},"metadata":{"description":"Claude Opus 4.6 is Anthropic’s latest state-of-the-art reasoning model. It features an adaptive “thinking” mode that dynamically decides when to think and how much to think. At the default effort level (high), Claude will almost always engage in thinking. At lower effort levels, it may skip thinking for simple problems.\n ⚠️ The minimum cache token for claude-opus-4-6 has been increased from 1,024 to 4,096 tokens.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text","image"],"pricing":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"azure-deepseek-v3.2","name":"azure-deepseek-v3.2","display_name":"azure-deepseek-v3.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.58,"output":1.680028},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.58,"output":1.680028},"source":"public-provider-conf"},"vision":false},{"id":"azure-deepseek-v3.2-speciale","name":"azure-deepseek-v3.2-speciale","display_name":"azure-deepseek-v3.2-speciale","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.58,"output":1.680028},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.58,"output":1.680028},"source":"public-provider-conf"},"vision":false},{"id":"cbs-glm-4.7","name":"cbs-glm-4.7","display_name":"cbs-glm-4.7","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.25,"output":2.749995},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2.25,"output":2.749995},"source":"public-provider-conf"},"vision":false},{"id":"cerebras-llama-3.3-70b","name":"cerebras-llama-3.3-70b","display_name":"cerebras-llama-3.3-70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.6,"output":0.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.6,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"chatglm_lite","name":"chatglm_lite","display_name":"chatglm_lite","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.2858,"output":0.2858},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.2858,"output":0.2858},"source":"public-provider-conf"},"vision":false},{"id":"chatglm_pro","name":"chatglm_pro","display_name":"chatglm_pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.4286,"output":1.4286},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.4286,"output":1.4286},"source":"public-provider-conf"},"vision":false},{"id":"chatglm_std","name":"chatglm_std","display_name":"chatglm_std","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.7144,"output":0.7144},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.7144,"output":0.7144},"source":"public-provider-conf"},"vision":false},{"id":"chatglm_turbo","name":"chatglm_turbo","display_name":"chatglm_turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.7144,"output":0.7144},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.7144,"output":0.7144},"source":"public-provider-conf"},"vision":false},{"id":"claude-2","name":"claude-2","display_name":"claude-2","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":8.8,"output":8.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":8.8,"output":8.8},"source":"public-provider-conf"},"vision":false},{"id":"claude-2.0","name":"claude-2.0","display_name":"claude-2.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":8.8,"output":39.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":8.8,"output":39.6},"source":"public-provider-conf"},"vision":false},{"id":"claude-2.1","name":"claude-2.1","display_name":"claude-2.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":8.8,"output":39.6},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":8.8,"output":39.6},"source":"public-provider-conf"},"vision":false},{"id":"claude-3-haiku-20240229","name":"claude-3-haiku-20240229","display_name":"claude-3-haiku-20240229","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.275,"output":0.275},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0.275,"output":0.275},"source":"public-provider-conf"},"vision":true},{"id":"claude-3-haiku-20240307","name":"claude-3-haiku-20240307","display_name":"claude-3-haiku-20240307","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.275,"output":1.375},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0.275,"output":1.375},"source":"public-provider-conf"},"vision":true},{"id":"claude-3-haiku@20240307","name":"claude-3-haiku@20240307","display_name":"claude-3-haiku@20240307","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":0.275,"output":1.375},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":0.275,"output":1.375},"source":"public-provider-conf"},"vision":true},{"id":"claude-3-opus@20240229","name":"claude-3-opus@20240229","display_name":"claude-3-opus@20240229","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":16.5,"output":82.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":16.5,"output":82.5},"source":"public-provider-conf"},"vision":false},{"id":"claude-3-sonnet-20240229","name":"claude-3-sonnet-20240229","display_name":"claude-3-sonnet-20240229","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"]},"cost":{"input":3.3,"output":16.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text","image"],"pricing":{"input":3.3,"output":16.5},"source":"public-provider-conf"},"vision":true},{"id":"claude-instant-1","name":"claude-instant-1","display_name":"claude-instant-1","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1.793,"output":1.793},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1.793,"output":1.793},"source":"public-provider-conf"},"vision":false},{"id":"claude-instant-1.2","name":"claude-instant-1.2","display_name":"claude-instant-1.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.88,"output":3.96},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.88,"output":3.96},"source":"public-provider-conf"},"vision":false},{"id":"code-davinci-edit-001","name":"code-davinci-edit-001","display_name":"code-davinci-edit-001","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":20,"output":20},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":20,"output":20},"source":"public-provider-conf"},"vision":false},{"id":"cogview-3","name":"cogview-3","display_name":"cogview-3","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"cost":{"input":35.5,"output":35.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation"],"pricing":{"input":35.5,"output":35.5},"source":"public-provider-conf"},"vision":false},{"id":"cogview-3-plus","name":"cogview-3-plus","display_name":"cogview-3-plus","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"cost":{"input":10,"output":10},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["image_generation"],"pricing":{"input":10,"output":10},"source":"public-provider-conf"},"vision":false},{"id":"command","name":"command","display_name":"command","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":1,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":1,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"command-light","name":"command-light","display_name":"command-light","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"command-light-nightly","name":"command-light-nightly","display_name":"command-light-nightly","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"command-nightly","name":"command-nightly","display_name":"command-nightly","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":1,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":1,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"command-r","name":"command-r","display_name":"command-r","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.64,"output":1.92},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.64,"output":1.92},"source":"public-provider-conf"},"vision":false},{"id":"command-r-08-2024","name":"command-r-08-2024","display_name":"command-r-08-2024","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":0.2,"output":0.8},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":0.2,"output":0.8},"source":"public-provider-conf"},"vision":false},{"id":"command-r-plus","name":"command-r-plus","display_name":"command-r-plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":3.84,"output":19.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":3.84,"output":19.2},"source":"public-provider-conf"},"vision":false},{"id":"command-r-plus-08-2024","name":"command-r-plus-08-2024","display_name":"command-r-plus-08-2024","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"cost":{"input":2.8,"output":11.2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"inputModalities":["text"],"pricing":{"input":2.8,"output":11.2},"source":"public-provider-conf"},"vision":false},{"id":"davinci","name":"davinci","display_name":"davinci","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":20,"output":20},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":20,"output":20},"source":"public-provider-conf"},"vision":false},{"id":"davinci-002","name":"davinci-002","display_name":"davinci-002","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2,"output":2},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":2,"output":2},"source":"public-provider-conf"},"vision":false},{"id":"deepinfra-llama-3.1-8b-instant","name":"deepinfra-llama-3.1-8b-instant","display_name":"deepinfra-llama-3.1-8b-instant","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.033,"output":0.054978},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.033,"output":0.054978},"source":"public-provider-conf"},"vision":false},{"id":"deepinfra-llama-3.3-70b-instant-turbo","name":"deepinfra-llama-3.3-70b-instant-turbo","display_name":"deepinfra-llama-3.3-70b-instant-turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.11,"output":0.352},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.11,"output":0.352},"source":"public-provider-conf"},"vision":false},{"id":"deepinfra-llama-4-maverick-17b-128e-instruct","name":"deepinfra-llama-4-maverick-17b-128e-instruct","display_name":"deepinfra-llama-4-maverick-17b-128e-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.33,"output":1.32},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.33,"output":1.32},"source":"public-provider-conf"},"vision":false},{"id":"deepinfra-llama-4-scout-17b-16e-instruct","name":"deepinfra-llama-4-scout-17b-16e-instruct","display_name":"deepinfra-llama-4-scout-17b-16e-instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.088,"output":0.33},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.088,"output":0.33},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-ai/DeepSeek-Coder-V2-Instruct","name":"deepseek-ai/DeepSeek-Coder-V2-Instruct","display_name":"deepseek-ai/DeepSeek-Coder-V2-Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.16,"output":0.32},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.16,"output":0.32},"source":"public-provider-conf"},"vision":false},{"id":"deepseek-r1-distill-qianfan-llama-8b","name":"deepseek-r1-distill-qianfan-llama-8b","display_name":"deepseek-r1-distill-qianfan-llama-8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.137,"output":0.548},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.137,"output":0.548},"source":"public-provider-conf"},"vision":false},{"id":"doubao-1-5-pro-256k-250115","name":"doubao-1-5-pro-256k-250115","display_name":"doubao-1-5-pro-256k-250115","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.684,"output":1.2312},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.684,"output":1.2312},"source":"public-provider-conf"},"vision":false},{"id":"doubao-1-5-pro-32k-250115","name":"doubao-1-5-pro-32k-250115","display_name":"doubao-1-5-pro-32k-250115","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.108,"output":0.27},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.108,"output":0.27},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4o-2024-08-06-global","name":"gpt-4o-2024-08-06-global","display_name":"gpt-4o-2024-08-06-global","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":2.5,"output":10,"cache_read":1.25},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":1.25,"input":2.5,"output":10},"source":"public-provider-conf"},"vision":false},{"id":"gpt-4o-mini-global","name":"gpt-4o-mini-global","display_name":"gpt-4o-mini-global","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.075,"input":0.15,"output":0.6},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama-3-70b","name":"meta-llama-3-70b","display_name":"meta-llama-3-70b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":4.795,"output":4.795},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":4.795,"output":4.795},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama-3-8b","name":"meta-llama-3-8b","display_name":"meta-llama-3-8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.548,"output":0.548},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.548,"output":0.548},"source":"public-provider-conf"},"vision":false},{"id":"o3-global","name":"o3-global","display_name":"o3-global","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":2,"output":8,"cache_read":0.5},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.5,"input":2,"output":8},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3-mini-global","name":"o3-mini-global","display_name":"o3-mini-global","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"cache_read":0.55,"input":1.1,"output":4.4},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3-pro-global","name":"o3-pro-global","display_name":"o3-pro-global","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"cost":{"input":20,"output":80},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":20,"output":80},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"qianfan-chinese-llama-2-13b","name":"qianfan-chinese-llama-2-13b","display_name":"qianfan-chinese-llama-2-13b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.822,"output":0.822},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.822,"output":0.822},"source":"public-provider-conf"},"vision":false},{"id":"qianfan-llama-vl-8b","name":"qianfan-llama-vl-8b","display_name":"qianfan-llama-vl-8b","type":"chat","reasoning":{"supported":false},"tool_call":false,"cost":{"input":0.274,"output":0.685},"limit":{"context":8192,"output":8192},"metadata":{"typeHints":["llm"],"pricing":{"input":0.274,"output":0.685},"source":"public-provider-conf"},"vision":false}],"metadata":{"source":"public-provider-conf"}},"openrouter":{"id":"openrouter","name":"OpenRouter","display_name":"OpenRouter","updated_at":"2026-10-18T20:13:13.847Z","models":[{"id":"~anthropic/claude-fable-latest","name":"Anthropic: Claude Fable Latest","display_name":"Anthropic: Claude Fable Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"~anthropic/claude-haiku-latest","name":"Anthropic: Claude Haiku Latest","display_name":"Anthropic: Claude Haiku Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"~anthropic/claude-opus-latest","name":"Anthropic: Claude Opus Latest","display_name":"Anthropic: Claude Opus Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"~anthropic/claude-sonnet-latest","name":"Anthropic: Claude Sonnet Latest","display_name":"Anthropic: Claude Sonnet Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"~deepseek/deepseek-flash-latest","name":"DeepSeek: DeepSeek Flash Latest","display_name":"DeepSeek: DeepSeek Flash Latest","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"high"}}},{"id":"~deepseek/deepseek-pro-latest","name":"DeepSeek: DeepSeek Pro Latest","display_name":"DeepSeek: DeepSeek Pro Latest","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"high"}}},{"id":"~deepseek/deepseek-v4-flash-latest","name":"DeepSeek: DeepSeek V4 Flash Latest","display_name":"DeepSeek: DeepSeek V4 Flash Latest","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"high"}}},{"id":"~google/gemini-flash-latest","name":"Google: Gemini Flash Latest","display_name":"Google: Gemini Flash Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"~google/gemini-pro-latest","name":"Google: Gemini Pro Latest","display_name":"Google: Gemini Pro Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["audio","image","text","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"~moonshotai/kimi-latest","name":"MoonshotAI: Kimi Latest","display_name":"MoonshotAI: Kimi Latest","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"max"}}},{"id":"~openai/gpt-astra-latest","name":"OpenAI: GPT Astra Latest","display_name":"OpenAI: GPT Astra Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"~openai/gpt-luna-latest","name":"OpenAI: GPT Luna Latest","display_name":"OpenAI: GPT Luna Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"~openai/gpt-mini-latest","name":"OpenAI: GPT Mini Latest","display_name":"OpenAI: GPT Mini Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","low","medium","high","xhigh"],"effort":"medium"}}},{"id":"~openai/gpt-sol-latest","name":"OpenAI: GPT Sol Latest","display_name":"OpenAI: GPT Sol Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"~openai/gpt-terra-latest","name":"OpenAI: GPT Terra Latest","display_name":"OpenAI: GPT Terra Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"~unbiased/pareto-latest","name":"Pareto Latest","display_name":"Pareto Latest","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"~x-ai/grok-latest","name":"xAI: Grok Latest","display_name":"xAI: Grok Latest","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":450000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh"],"effort":"high"}}},{"id":"~z-ai/glm-flash-latest","name":"Z.ai: GLM Flash Latest","display_name":"Z.ai: GLM Flash Latest","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"max"}}},{"id":"~z-ai/glm-latest","name":"Z.ai: GLM Latest","display_name":"Z.ai: GLM Latest","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"max"}}},{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","display_name":"AionLabs: Aion-2.0","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion-3.0","display_name":"AionLabs: Aion-3.0","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","display_name":"AionLabs: Aion-3.0-Mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"aion-labs/aion-3.5","name":"AionLabs: Aion 3.5","display_name":"AionLabs: Aion 3.5","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"high"}}},{"id":"aion-labs/aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","display_name":"AionLabs: Aion 3.5 Mini","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"high"}}},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","display_name":"AionLabs: Aion-RP 1.0 (8B)","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":29491},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","display_name":"Amazon: Nova 2 Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":65535},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","display_name":"Amazon: Nova Lite 1.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":300000,"output":5120},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","display_name":"Amazon: Nova Micro 1.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":5120},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","display_name":"Amazon: Nova Premier 1.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","display_name":"Amazon: Nova Pro 1.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":300000,"output":5120},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","display_name":"Magnum v4 72B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","display_name":"Anthropic: Claude Fable 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","display_name":"Anthropic: Claude Fable 5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","display_name":"Anthropic: Claude Fable 5.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5.1:batch","name":"Anthropic: Claude Fable 5.1 (batch)","display_name":"Anthropic: Claude Fable 5.1 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","display_name":"Anthropic: Claude Haiku 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."],"effort_options":[]}}},{"id":"anthropic/claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","display_name":"Anthropic: Claude Haiku 4.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."],"effort_options":[]}}},{"id":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","display_name":"Anthropic: Claude Haiku 5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"anthropic/claude-haiku-5.5:batch","name":"Anthropic: Claude Haiku 5.5 (batch)","display_name":"Anthropic: Claude Haiku 5.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","display_name":"Anthropic: Claude Opus 4.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."],"effort_options":[]}}},{"id":"anthropic/claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","display_name":"Anthropic: Claude Opus 4.1 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."],"effort_options":[]}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","display_name":"Anthropic: Claude Opus 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":[],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","display_name":"Anthropic: Claude Opus 4.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":[],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","display_name":"Anthropic: Claude Opus 4.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["none","low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","display_name":"Anthropic: Claude Opus 4.6 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["none","low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","display_name":"Anthropic: Claude Opus 4.7","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["none","low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","display_name":"Anthropic: Claude Opus 4.7 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["none","low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","display_name":"Anthropic: Claude Opus 4.8","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["none","low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","display_name":"Anthropic: Claude Opus 4.8 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["none","low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","display_name":"Anthropic: Claude Opus 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","medium","high","xhigh","max"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"anthropic/claude-opus-5:batch","name":"Anthropic: Claude Opus 5 (batch)","display_name":"Anthropic: Claude Opus 5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","display_name":"Anthropic: Claude Opus 5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"anthropic/claude-opus-5.5:batch","name":"Anthropic: Claude Opus 5.5 (batch)","display_name":"Anthropic: Claude Opus 5.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","display_name":"Anthropic: Claude Sonnet 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."],"effort_options":[]}}},{"id":"anthropic/claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","display_name":"Anthropic: Claude Sonnet 4.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."],"effort_options":[]}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","display_name":"Anthropic: Claude Sonnet 4.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","budget":{"min":1024,"unit":"tokens"},"effort":"medium","effort_options":["none","low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-4.6:batch","name":"Anthropic: Claude Sonnet 4.6 (batch)","display_name":"Anthropic: Claude Sonnet 4.6 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","budget":{"min":1024,"unit":"tokens"},"effort":"medium","effort_options":["none","low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","display_name":"Anthropic: Claude Sonnet 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","medium","high","xhigh","max"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"anthropic/claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","display_name":"Anthropic: Claude Sonnet 5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","display_name":"Anthropic: Claude Sonnet 5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"anthropic/claude-sonnet-5.5:batch","name":"Anthropic: Claude Sonnet 5.5 (batch)","display_name":"Anthropic: Claude Sonnet 5.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"high"}}},{"id":"arcee-ai/trinity-large-thinking","name":"Arcee AI: Trinity Large Thinking","display_name":"Arcee AI: Trinity Large Thinking","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":80000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6","display_name":"ByteDance Seed: Seed 1.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","display_name":"ByteDance Seed: Seed 1.6 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"bytedance-seed/seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","display_name":"ByteDance Seed: Seed 2.1 Turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"bytedance-seed/seed-2.0-code","name":"ByteDance Seed: Seed-2.0-Code","display_name":"ByteDance Seed: Seed-2.0-Code","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high"],"effort":"medium"}}},{"id":"bytedance-seed/seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","display_name":"ByteDance Seed: Seed-2.0-Lite","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high"],"effort":"medium"}}},{"id":"bytedance-seed/seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","display_name":"ByteDance Seed: Seed-2.0-Mini","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high"],"effort":"medium"}}},{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B","display_name":"ByteDance: UI-TARS 7B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":128000,"output":2048},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","display_name":"Venice: Uncensored","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"cohere/command-a","name":"Cohere: Command A","display_name":"Cohere: Command A","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":256000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"cohere/command-a-plus","name":"Cohere: Command A+","display_name":"Cohere: Command A+","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":192000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","display_name":"Cohere: Command R (08-2024)","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":4000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","display_name":"Cohere: Command R+ (08-2024)","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":4000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","display_name":"Cohere: Command R7B (12-2024)","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":4000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"cohere/north-mini-code:free","name":"Cohere: North Mini Code (free)","display_name":"Cohere: North Mini Code (free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":256000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","display_name":"DeepSeek: DeepSeek V3","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","display_name":"DeepSeek: DeepSeek V3 0324","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":115200},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","display_name":"DeepSeek: DeepSeek V3.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"deepseek/deepseek-r1","name":"DeepSeek: R1","display_name":"DeepSeek: R1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":64000,"output":16000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","display_name":"DeepSeek: R1 0528","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","display_name":"DeepSeek: DeepSeek V3.1 Terminus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":147456},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","display_name":"DeepSeek: DeepSeek V3.2","type":"chat","reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":false}}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","display_name":"DeepSeek: DeepSeek V3.2 Exp","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":147456},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","display_name":"DeepSeek: DeepSeek V4 Flash 0423","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","xhigh"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048575,"output":943717},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["none","high","xhigh"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","display_name":"DeepSeek: DeepSeek V4 Flash 0731","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","high","max"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","display_name":"DeepSeek: DeepSeek V4 Flash Vision Exp","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["none","low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","display_name":"DeepSeek: DeepSeek V4 Pro 0423","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","xhigh"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1024000,"output":384000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["none","high","xhigh"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","display_name":"DeepSeek: DeepSeek V4 Pro 0813","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1024000,"output":384000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","high","max"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","display_name":"DeepSeek: DeepSeek V4.1 Flash","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","high","max"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","display_name":"DeepSeek: DeepSeek V4.1 Flash 1017","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"high"}}},{"id":"deepseek/deepseek-v4.1-flash:batch","name":"DeepSeek: DeepSeek V4.1 Flash (batch)","display_name":"DeepSeek: DeepSeek V4.1 Flash (batch)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":384000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"high"}}},{"id":"dots-studio/dots-3-note-preview:free","name":"Dots Studio: Dots3-Note Preview (free)","display_name":"Dots Studio: Dots3-Note Preview (free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":512000,"output":460800},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"elorian/glimpse","name":"Elorian: Glimpse","display_name":"Elorian: Glimpse","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":256000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"fireworks/ember-1","name":"Fireworks: Ember-1","display_name":"Fireworks: Ember-1","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"max"}}},{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","display_name":"Google: Gemini 2.5 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65535},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","display_name":"Google: Nano Banana (Gemini 2.5 Flash Image)","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":32768,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","display_name":"Google: Gemini 2.5 Flash Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65535},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-2.5-flash-lite:batch","name":"Google: Gemini 2.5 Flash Lite (batch)","display_name":"Google: Gemini 2.5 Flash Lite (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65535},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-2.5-flash:batch","name":"Google: Gemini 2.5 Flash (batch)","display_name":"Google: Gemini 2.5 Flash (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65535},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","display_name":"Google: Gemini 2.5 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text","image","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","display_name":"Google: Gemini 2.5 Pro Preview 06-05","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["image","text","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-2.5-pro:batch","name":"Google: Gemini 2.5 Pro (batch)","display_name":"Google: Gemini 2.5 Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text","image","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","display_name":"Google: Gemini 3 Flash Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["none","minimal","low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3-flash-preview:batch","name":"Google: Gemini 3 Flash Preview (batch)","display_name":"Google: Gemini 3 Flash Preview (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","audio","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["none","minimal","low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3-pro-image","name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","display_name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":65536,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","display_name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":65536,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":[]}}},{"id":"google/gemini-3.1-flash-image","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","display_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","type":"image-generation","reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","high"]}],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","minimal","high"],"default_enabled":true,"mode":"effort","effort":"minimal"}}},{"id":"google/gemini-3.1-flash-image-preview","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","display_name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","type":"image-generation","reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","high"]}],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":65536,"output":58982},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","minimal","high"],"default_enabled":true,"mode":"effort","effort":"minimal"}}},{"id":"google/gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","display_name":"Google: Gemini 3.1 Flash Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","minimal","low","medium","high"],"default_enabled":true,"mode":"effort","effort":"minimal"}}},{"id":"google/gemini-3.1-flash-lite-image","name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","display_name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","type":"image-generation","reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","high"]}],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":65536,"output":58982},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","minimal","high"],"default_enabled":true,"mode":"effort","effort":"minimal"}}},{"id":"google/gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","display_name":"Google: Gemini 3.1 Flash Lite Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high"],"effort":"minimal"}}},{"id":"google/gemini-3.1-flash-lite:batch","name":"Google: Gemini 3.1 Flash Lite (batch)","display_name":"Google: Gemini 3.1 Flash Lite (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high"],"effort":"minimal"}}},{"id":"google/gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","display_name":"Google: Gemini 3.1 Pro Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["audio","image","text","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","display_name":"Google: Gemini 3.1 Pro Preview Custom Tools","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","audio","image","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.1-pro-preview:batch","name":"Google: Gemini 3.1 Pro Preview (batch)","display_name":"Google: Gemini 3.1 Pro Preview (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["audio","image","text","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","display_name":"Google: Gemini 3.5 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["minimal","low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","display_name":"Google: Gemini 3.5 Flash Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["minimal","low","medium","high"],"default_enabled":true,"mode":"effort","effort":"minimal"}}},{"id":"google/gemini-3.5-flash-lite:batch","name":"Google: Gemini 3.5 Flash Lite (batch)","display_name":"Google: Gemini 3.5 Flash Lite (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high"],"effort":"minimal"}}},{"id":"google/gemini-3.5-flash:batch","name":"Google: Gemini 3.5 Flash (batch)","display_name":"Google: Gemini 3.5 Flash (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["minimal","low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","display_name":"Google: Gemini 3.6 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["minimal","low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.6-flash:batch","name":"Google: Gemini 3.6 Flash (batch)","display_name":"Google: Gemini 3.6 Flash (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["minimal","low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","display_name":"Google: Gemini 3.7 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.7-flash:batch","name":"Google: Gemini 3.7 Flash (batch)","display_name":"Google: Gemini 3.7 Flash (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","display_name":"Google: Gemini 3.8 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-3.8-flash:batch","name":"Google: Gemini 3.8 Flash (batch)","display_name":"Google: Gemini 3.8 Flash (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"],"effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-4-argon","name":"Google: Gemini 4 Argon","display_name":"Google: Gemini 4 Argon","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["audio","image","text","video"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-4-argon:batch","name":"Google: Gemini 4 Argon (batch)","display_name":"Google: Gemini 4 Argon (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["audio","image","text","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"google/gemini-nano-banana-2.1","name":"Google: Nano Banana 2.1","display_name":"Google: Nano Banana 2.1","type":"image-generation","reasoning":{"supported":true,"default":true,"effort":"minimal"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","high"]}],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":65536,"output":58982},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","high"],"effort":"minimal"}}},{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","display_name":"Google: Gemma 2 27B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":2048},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","display_name":"Google: Gemma 3 12B","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","display_name":"Google: Gemma 3 27B","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","display_name":"Google: Gemma 3 4B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B","display_name":"Google: Gemma 4 26B A4B","type":"chat","reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"effort_options":[]}}},{"id":"google/gemma-4-26b-a4b-it:free","name":"Google: Gemma 4 26B A4B  (free)","display_name":"Google: Gemma 4 26B A4B  (free)","type":"chat","reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"effort_options":[]}}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","display_name":"Google: Gemma 4 31B","type":"chat","reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":262144,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"effort_options":[]}}},{"id":"google/gemma-4-31b-it:free","name":"Google: Gemma 4 31B (free)","display_name":"Google: Gemma 4 31B (free)","type":"chat","reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"effort_options":[]}}},{"id":"google/lyria-3-clip-preview","name":"Google: Lyria 3 Clip Preview","display_name":"Google: Lyria 3 Clip Preview","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text","audio"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"google/lyria-3-pro-preview","name":"Google: Lyria 3 Pro Preview","display_name":"Google: Lyria 3 Pro Preview","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text","audio"]},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","display_name":"MythoMax 13B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":4096,"output":3686},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","display_name":"IBM: Granite 4.0 Micro","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131000,"output":117900},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"ibm-granite/granite-4.2-8b","name":"IBM: Granite 4.2 8B","display_name":"IBM: Granite 4.2 8B","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high"],"effort":"high"}}},{"id":"inception/mercury-2","name":"Inception: Mercury 2","display_name":"Inception: Mercury 2","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":50000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high"],"effort":"medium"}}},{"id":"inception/mercury-2.5","name":"Inception: Mercury 2.5","display_name":"Inception: Mercury 2.5","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":260000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high"],"effort":"medium"}}},{"id":"inclusionai/ling-3.0-flash","name":"inclusionAI: Ling 3.0 Flash","display_name":"inclusionAI: Ling 3.0 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"inclusionai/ling-3.0-flash-vl","name":"inclusionAI: Ling 3.0 Flash VL","display_name":"inclusionAI: Ling 3.0 Flash VL","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"inclusionai/ling-3.1-flash","name":"inclusionAI: Ling 3.1 Flash","display_name":"inclusionAI: Ling 3.1 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"inference-net/schematron-v2-small","name":"Inference.net: Schematron V2 Small","display_name":"Inference.net: Schematron V2 Small","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"inference-net/schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","display_name":"Inference.net: Schematron V2 Turbo","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"liquid/lfm-2.5-2.6b:free","name":"LiquidAI: LFM2.5-2.6B (free)","display_name":"LiquidAI: LFM2.5-2.6B (free)","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":65536,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"liquid/lfm-2.5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","display_name":"LiquidAI: LFM2.5-24B-A2B","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","display_name":"Mancer: Weaver (alpha)","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8000,"output":6000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"meituan/longcat-2.0","name":"Meituan: LongCat 2.0","display_name":"Meituan: LongCat 2.0","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048756,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","display_name":"Meta: Llama 3.1 70B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","display_name":"Meta: Llama 3.1 8B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","display_name":"Meta: Llama 3.2 1B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":60000,"output":54000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","display_name":"Meta: Llama 3.2 3B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","display_name":"Meta: Llama 3.3 70B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","display_name":"Meta: Llama 4 Maverick","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","display_name":"Meta: Llama 4 Scout","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":327680,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","display_name":"Meta: Llama Guard 4 12B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":163840,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"meta/muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","display_name":"Meta: Muse Glimmer 30B","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh"],"effort":"medium"}}},{"id":"meta/muse-spark-1.1","name":"Meta: Muse Spark 1.1","display_name":"Meta: Muse Spark 1.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["minimal","low","medium","high","xhigh"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"meta/muse-spark-1.2","name":"Meta: Muse Spark 1.2","display_name":"Meta: Muse Spark 1.2","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["minimal","low","medium","high","xhigh"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"meta/muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","display_name":"Meta: Muse Spark 1.2 Contributor","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high","xhigh"],"effort":"medium"}}},{"id":"meta/muse-spark-1.3","name":"Meta: Muse Spark 1.3","display_name":"Meta: Muse Spark 1.3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["minimal","low","medium","high","xhigh","max"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"meta/muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","display_name":"Meta: Muse Spark 1.3 Contributor","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"meta/muse-spark-open","name":"Meta: Muse Spark Open","display_name":"Meta: Muse Spark Open","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh"],"effort":"medium"}}},{"id":"meta/muse-wonder","name":"Meta: Muse Wonder","display_name":"Meta: Muse Wonder","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"microsoft/phi-4","name":"Microsoft: Phi 4","display_name":"Microsoft: Phi 4","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":16384,"output":14745},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","display_name":"WizardLM-2 8x22B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":65535,"output":8000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","display_name":"MiniMax: MiniMax-01","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000192,"output":900172},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","display_name":"MiniMax: MiniMax M1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":40000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","display_name":"MiniMax: MiniMax M2","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"minimax/minimax-m2-her","name":"MiniMax: MiniMax M2-her","display_name":"MiniMax: MiniMax M2-her","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":65536,"output":2048},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","display_name":"MiniMax: MiniMax M2.1","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","display_name":"MiniMax: MiniMax M2.5","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":198000,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","display_name":"MiniMax: MiniMax M2.7","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","display_name":"MiniMax: MiniMax M3","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":524288,"output":512000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","display_name":"Mistral: Codestral 2508","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":256000,"output":204800},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/codestral-2508:batch","name":"Mistral: Codestral 2508 (batch)","display_name":"Mistral: Codestral 2508 (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":256000,"output":204800},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/devstral-2512","name":"Mistral: Devstral 2 2512","display_name":"Mistral: Devstral 2 2512","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","display_name":"Mistral: Ministral 3 14B 2512","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","display_name":"Mistral: Ministral 3 3B 2512","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":104857},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","display_name":"Mistral: Ministral 3 8B 2512","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/ministral-8b-2512:batch","name":"Mistral: Ministral 3 8B 2512 (batch)","display_name":"Mistral: Ministral 3 8B 2512 (batch)","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-large","name":"Mistral Large","display_name":"Mistral Large","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":102400},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","display_name":"Mistral Large 2407","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":104857},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/mistral-large-2512","name":"Mistral: Mistral Large 3 2512","display_name":"Mistral: Mistral Large 3 2512","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-large-2512:batch","name":"Mistral: Mistral Large 3 2512 (batch)","display_name":"Mistral: Mistral Large 3 2512 (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-large-4-0","name":"Mistral: Mistral Large 4","display_name":"Mistral: Mistral Large 4","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","high"],"effort":"high"}}},{"id":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","display_name":"Mistral: Mistral Medium 3","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":104857},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","display_name":"Mistral: Mistral Medium 3.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","high"],"effort":"high"}}},{"id":"mistralai/mistral-medium-3-5:batch","name":"Mistral: Mistral Medium 3.5 (batch)","display_name":"Mistral: Mistral Medium 3.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","high"],"effort":"high"}}},{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","display_name":"Mistral: Mistral Medium 3.1","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":104857},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-medium-3.1:batch","name":"Mistral: Mistral Medium 3.1 (batch)","display_name":"Mistral: Mistral Medium 3.1 (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":104857},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","display_name":"Mistral: Mistral Nemo","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/mistral-saba","name":"Mistral: Saba","display_name":"Mistral: Saba","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":26214},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","display_name":"Mistral: Mistral Small 3","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/mistral-small-2603","name":"Mistral: Mistral Small 4","display_name":"Mistral: Mistral Small 4","type":"chat","reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","high"],"effort":"high"}}},{"id":"mistralai/mistral-small-2603:batch","name":"Mistral: Mistral Small 4 (batch)","display_name":"Mistral: Mistral Small 4 (batch)","type":"chat","reasoning":{"supported":true,"default":false,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","high"],"effort":"high"}}},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","display_name":"Mistral: Mistral Small 3.1 24B","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":102400},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","display_name":"Mistral: Mistral Small 3.2 24B","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":256000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","display_name":"Mistral: Mixtral 8x22B Instruct","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":65536,"output":52428},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","display_name":"Mistral: Voxtral Small 24B 2507","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","audio"],"output":["text"]},"limit":{"context":32768,"output":26214},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"moondream/moondream3-preview","name":"Moondream: Moondream 3 Preview","display_name":"Moondream: Moondream 3 Preview","type":"chat","reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":32000,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"effort_options":[]}}},{"id":"moondream/moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","display_name":"Moondream: Moondream 3.1","type":"chat","reasoning":{"supported":true,"default":false},"temperature":true,"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":32000,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"effort_options":[]}}},{"id":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","display_name":"MoonshotAI: Kimi K2 0711","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":98304},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","display_name":"MoonshotAI: Kimi K2 0905","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":98304},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","display_name":"MoonshotAI: Kimi K2 Thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":98304},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","display_name":"MoonshotAI: Kimi K2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","display_name":"MoonshotAI: Kimi K2.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","display_name":"MoonshotAI: Kimi K2.7 Code","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","display_name":"MoonshotAI: Kimi K3","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","high","max"],"default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"moonshotai/kimi-k3:batch","name":"MoonshotAI: Kimi K3 (batch)","display_name":"MoonshotAI: Kimi K3 (batch)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high","max"],"effort":"max"}}},{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","display_name":"Morph: Morph V3 Fast","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":81920,"output":38000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","display_name":"Morph: Morph V3 Large","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"nex-agi/nex-n2.5-mini","name":"Nex AGI: Nex-N2.5-Mini","display_name":"Nex AGI: Nex-N2.5-Mini","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","medium","high"],"effort":"high"}}},{"id":"nex-agi/nex-n2.5-pro","name":"Nex AGI: Nex-N2.5-Pro","display_name":"Nex AGI: Nex-N2.5-Pro","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","medium","high"],"effort":"high"}}},{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","display_name":"Nous: Hermes 3 405B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","display_name":"Nous: Hermes 3 70B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","display_name":"Nous: Hermes 4 405B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","display_name":"NVIDIA: Nemotron 3 Nano 30B A3B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","name":"NVIDIA: Nemotron 3 Nano Omni (free)","display_name":"NVIDIA: Nemotron 3 Nano Omni (free)","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","audio","image","video"],"output":["text"]},"limit":{"context":256000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","display_name":"NVIDIA: Nemotron 3 Super","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","medium"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"nvidia/nemotron-3-super-120b-a12b:free","name":"NVIDIA: Nemotron 3 Super (free)","display_name":"NVIDIA: Nemotron 3 Super (free)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium"],"effort":"medium"}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","display_name":"NVIDIA: Nemotron 3 Ultra","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":202800,"output":182520},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","medium","high"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","name":"NVIDIA: Nemotron 3 Ultra (free)","display_name":"NVIDIA: Nemotron 3 Ultra (free)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","medium","high"],"effort":"high"}}},{"id":"nvidia/nemotron-3.5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","display_name":"NVIDIA: Nemotron 3.5 Content Safety","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"nvidia/nemotron-3.5-content-safety:free","name":"NVIDIA: Nemotron 3.5 Content Safety (free)","display_name":"NVIDIA: Nemotron 3.5 Content Safety (free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"nvidia/nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","display_name":"NVIDIA: Nemotron 3.5 Lightning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"nvidia/nemotron-3.5-lightning:free","name":"NVIDIA: Nemotron 3.5 Lightning (free)","display_name":"NVIDIA: Nemotron 3.5 Lightning (free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"nvidia/nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","display_name":"NVIDIA: Nemotron 3.5 Super VL","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"nvidia/nemotron-3.5-super-vl:free","name":"NVIDIA: Nemotron 3.5 Super VL (free)","display_name":"NVIDIA: Nemotron 3.5 Super VL (free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"nvidia/switchyard","name":"NVIDIA: Switchyard","display_name":"NVIDIA: Switchyard","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo","display_name":"OpenAI: GPT-3.5 Turbo","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":16385,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","display_name":"OpenAI: GPT-3.5 Turbo (older v0613)","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":4095,"output":3685},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","display_name":"OpenAI: GPT-3.5 Turbo 16k","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":16385,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","display_name":"OpenAI: GPT-3.5 Turbo Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":4095,"output":3685},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-3.5-turbo:batch","name":"OpenAI: GPT-3.5 Turbo (batch)","display_name":"OpenAI: GPT-3.5 Turbo (batch)","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":16385,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-4","name":"OpenAI: GPT-4","display_name":"OpenAI: GPT-4","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8191,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","display_name":"OpenAI: GPT-4 Turbo","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4-turbo:batch","name":"OpenAI: GPT-4 Turbo (batch)","display_name":"OpenAI: GPT-4 Turbo (batch)","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","display_name":"OpenAI: GPT-4.1","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","display_name":"OpenAI: GPT-4.1 Mini","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1-mini:batch","name":"OpenAI: GPT-4.1 Mini (batch)","display_name":"OpenAI: GPT-4.1 Mini (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","display_name":"OpenAI: GPT-4.1 Nano","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1-nano:batch","name":"OpenAI: GPT-4.1 Nano (batch)","display_name":"OpenAI: GPT-4.1 Nano (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1:batch","name":"OpenAI: GPT-4.1 (batch)","display_name":"OpenAI: GPT-4.1 (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o","name":"OpenAI: GPT-4o","display_name":"OpenAI: GPT-4o","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","display_name":"OpenAI: GPT-4o (2024-05-13)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","display_name":"OpenAI: GPT-4o (2024-08-06)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","display_name":"OpenAI: GPT-4o (2024-11-20)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","display_name":"OpenAI: GPT-4o-mini","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","display_name":"OpenAI: GPT-4o-mini (2024-07-18)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o-mini:batch","name":"OpenAI: GPT-4o-mini (batch)","display_name":"OpenAI: GPT-4o-mini (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o:batch","name":"OpenAI: GPT-4o (batch)","display_name":"OpenAI: GPT-4o (batch)","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","display_name":"OpenAI: GPT-5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-image","name":"OpenAI: GPT-5 Image","display_name":"OpenAI: GPT-5 Image","type":"image-generation","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"openai/gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","display_name":"OpenAI: GPT-5 Image Mini","type":"image-generation","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","display_name":"OpenAI: GPT-5 Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-mini:batch","name":"OpenAI: GPT-5 Mini (batch)","display_name":"OpenAI: GPT-5 Mini (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high"],"effort":"medium"}}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","display_name":"OpenAI: GPT-5 Nano","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-nano:batch","name":"OpenAI: GPT-5 Nano (batch)","display_name":"OpenAI: GPT-5 Nano (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high"],"effort":"medium"}}},{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","display_name":"OpenAI: GPT-5 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["high"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-pro:batch","name":"OpenAI: GPT-5 Pro (batch)","display_name":"OpenAI: GPT-5 Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["high"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["high"],"effort":"high"}}},{"id":"openai/gpt-5:batch","name":"OpenAI: GPT-5 (batch)","display_name":"OpenAI: GPT-5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high"],"effort":"medium"}}},{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","display_name":"OpenAI: GPT-5.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","display_name":"OpenAI: GPT-5.1-Codex","type":"chat","reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","display_name":"OpenAI: GPT-5.1-Codex-Max","type":"chat","reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","display_name":"OpenAI: GPT-5.1-Codex-Mini","type":"chat","reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1:batch","name":"OpenAI: GPT-5.1 (batch)","display_name":"OpenAI: GPT-5.1 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","low","medium","high"],"effort":"medium"}}},{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","display_name":"OpenAI: GPT-5.2","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","display_name":"OpenAI: GPT-5.2 Chat","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":128000,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","display_name":"OpenAI: GPT-5.2-Codex","type":"chat","reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","display_name":"OpenAI: GPT-5.2 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-pro:batch","name":"OpenAI: GPT-5.2 Pro (batch)","display_name":"OpenAI: GPT-5.2 Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2:batch","name":"OpenAI: GPT-5.2 (batch)","display_name":"OpenAI: GPT-5.2 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh"],"effort":"medium"}}},{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","display_name":"OpenAI: GPT-5.3-Codex","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","display_name":"OpenAI: GPT-5.4","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","display_name":"OpenAI: GPT-5.4 Image 2","type":"image-generation","attachment":true,"reasoning":{"supported":true,"default":false,"verbosity":"medium","effort":"medium"},"tool_call":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["image","text"]},"limit":{"context":272000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","display_name":"OpenAI: GPT-5.4 Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-mini:batch","name":"OpenAI: GPT-5.4 Mini (batch)","display_name":"OpenAI: GPT-5.4 Mini (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","display_name":"OpenAI: GPT-5.4 Nano","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-nano:batch","name":"OpenAI: GPT-5.4 Nano (batch)","display_name":"OpenAI: GPT-5.4 Nano (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","display_name":"OpenAI: GPT-5.4 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro:batch","name":"OpenAI: GPT-5.4 Pro (batch)","display_name":"OpenAI: GPT-5.4 Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4:batch","name":"OpenAI: GPT-5.4 (batch)","display_name":"OpenAI: GPT-5.4 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","low","medium","high","xhigh"],"effort":"medium"}}},{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","display_name":"OpenAI: GPT-5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","display_name":"OpenAI: GPT-5.5 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["medium","high","xhigh"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"openai/gpt-5.5-pro:batch","name":"OpenAI: GPT-5.5 Pro (batch)","display_name":"OpenAI: GPT-5.5 Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["medium","high","xhigh"],"effort":"medium"}}},{"id":"openai/gpt-5.5:batch","name":"OpenAI: GPT-5.5 (batch)","display_name":"OpenAI: GPT-5.5 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh"],"effort":"medium"}}},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","display_name":"OpenAI: GPT-5.6 Luna","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","display_name":"OpenAI: GPT-5.6 Luna Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-luna-pro:batch","name":"OpenAI: GPT-5.6 Luna Pro (batch)","display_name":"OpenAI: GPT-5.6 Luna Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-luna:batch","name":"OpenAI: GPT-5.6 Luna (batch)","display_name":"OpenAI: GPT-5.6 Luna (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","display_name":"OpenAI: GPT-5.6 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","display_name":"OpenAI: GPT-5.6 Sol Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-sol-pro:batch","name":"OpenAI: GPT-5.6 Sol Pro (batch)","display_name":"OpenAI: GPT-5.6 Sol Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-sol:batch","name":"OpenAI: GPT-5.6 Sol (batch)","display_name":"OpenAI: GPT-5.6 Sol (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","display_name":"OpenAI: GPT-5.6 Terra","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"verbosity":"medium","effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","display_name":"OpenAI: GPT-5.6 Terra Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-terra-pro:batch","name":"OpenAI: GPT-5.6 Terra Pro (batch)","display_name":"OpenAI: GPT-5.6 Terra Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-5.6-terra:batch","name":"OpenAI: GPT-5.6 Terra (batch)","display_name":"OpenAI: GPT-5.6 Terra (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","display_name":"OpenAI: GPT-6 Astra","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","high","xhigh","max"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"openai/gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","display_name":"OpenAI: GPT-6 Astra Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-astra-pro:batch","name":"OpenAI: GPT-6 Astra Pro (batch)","display_name":"OpenAI: GPT-6 Astra Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-astra:batch","name":"OpenAI: GPT-6 Astra (batch)","display_name":"OpenAI: GPT-6 Astra (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","display_name":"OpenAI: GPT-6 Luna","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","display_name":"OpenAI: GPT-6 Luna Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-luna-pro:batch","name":"OpenAI: GPT-6 Luna Pro (batch)","display_name":"OpenAI: GPT-6 Luna Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-luna:batch","name":"OpenAI: GPT-6 Luna (batch)","display_name":"OpenAI: GPT-6 Luna (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","display_name":"OpenAI: GPT-6 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","display_name":"OpenAI: GPT-6 Sol Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-sol-pro:batch","name":"OpenAI: GPT-6 Sol Pro (batch)","display_name":"OpenAI: GPT-6 Sol Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6-sol:batch","name":"OpenAI: GPT-6 Sol (batch)","display_name":"OpenAI: GPT-6 Sol (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","display_name":"OpenAI: GPT-6.1 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","display_name":"OpenAI: GPT-6.1 Sol Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6.1-sol-pro:batch","name":"OpenAI: GPT-6.1 Sol Pro (batch)","display_name":"OpenAI: GPT-6.1 Sol Pro (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-6.1-sol:batch","name":"OpenAI: GPT-6.1 Sol (batch)","display_name":"OpenAI: GPT-6.1 Sol (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"openai/gpt-audio","name":"OpenAI: GPT Audio","display_name":"OpenAI: GPT Audio","type":"audio","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","audio"],"output":["text","audio"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-audio-mini","name":"OpenAI: GPT Audio Mini","display_name":"OpenAI: GPT Audio Mini","type":"audio","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","audio"],"output":["text","audio"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","display_name":"OpenAI: GPT Chat Latest","type":"chat","attachment":true,"reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","display_name":"OpenAI: gpt-oss-120b","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","high"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"openai/gpt-oss-120b:batch","name":"OpenAI: gpt-oss-120b (batch)","display_name":"OpenAI: gpt-oss-120b (batch)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","display_name":"OpenAI: gpt-oss-20b","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","high"],"default_enabled":true,"mode":"effort","effort":"medium"}}},{"id":"openai/gpt-oss-20b:batch","name":"OpenAI: gpt-oss-20b (batch)","display_name":"OpenAI: gpt-oss-20b (batch)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","display_name":"OpenAI: gpt-oss-safeguard-20b","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"openai/o1","name":"OpenAI: o1","display_name":"OpenAI: o1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"medium","effort_options":[],"visibility":"hidden"}}},{"id":"openai/o1-pro","name":"OpenAI: o1-pro","display_name":"OpenAI: o1-pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"medium","effort_options":[],"visibility":"hidden"}}},{"id":"openai/o3","name":"OpenAI: o3","display_name":"OpenAI: o3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"medium","effort_options":[],"visibility":"hidden"}}},{"id":"openai/o3-mini","name":"OpenAI: o3 Mini","display_name":"OpenAI: o3 Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"medium","effort_options":[],"visibility":"hidden"}}},{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","display_name":"OpenAI: o3 Mini High","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["high"],"visibility":"hidden"}}},{"id":"openai/o3-mini:batch","name":"OpenAI: o3 Mini (batch)","display_name":"OpenAI: o3 Mini (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"medium","effort_options":[],"visibility":"hidden"}}},{"id":"openai/o3-pro","name":"OpenAI: o3 Pro","display_name":"OpenAI: o3 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"medium","effort_options":[],"visibility":"hidden"}}},{"id":"openai/o3:batch","name":"OpenAI: o3 (batch)","display_name":"OpenAI: o3 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","display_name":"OpenAI: o4 Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"medium","effort_options":[],"visibility":"hidden"}}},{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","display_name":"OpenAI: o4 Mini High","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["high"]}],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["high"],"visibility":"hidden"}}},{"id":"openai/o4-mini:batch","name":"OpenAI: o4 Mini (batch)","display_name":"OpenAI: o4 Mini (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"openrouter/auto","name":"Auto Router","display_name":"Auto Router","type":"image-generation","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","audio","video"],"output":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openrouter/auto-beta","name":"Auto Router (Beta)","display_name":"Auto Router (Beta)","type":"image-generation","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","audio","video"],"output":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openrouter/bodybuilder","name":"Body Builder (beta)","display_name":"Body Builder (beta)","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openrouter/free","name":"Free Models Router","display_name":"Free Models Router","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openrouter/fusion","name":"OpenRouter: Fusion","display_name":"OpenRouter: Fusion","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openrouter/pareto-code","name":"Pareto Code Router","display_name":"Pareto Code Router","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"perceptron/perceptron-mk1","name":"Perceptron: Perceptron Mk1","display_name":"Perceptron: Perceptron Mk1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":32768,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"perceptron/perceptron-mk1.5","name":"Perceptron: Perceptron Mk1.5","display_name":"Perceptron: Perceptron Mk1.5","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":36864,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high"],"effort":"high"}}},{"id":"perplexity/sonar","name":"Perplexity: Sonar","display_name":"Perplexity: Sonar","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":127072,"output":114364},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","display_name":"Perplexity: Sonar Deep Research","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":115200},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","display_name":"Perplexity: Sonar Pro","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":8000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","display_name":"Perplexity: Sonar Pro Search","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":8000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","display_name":"Perplexity: Sonar Reasoning Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":115200},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"poolside/laguna-s-2.1","name":"Poolside: Laguna S 2.1","display_name":"Poolside: Laguna S 2.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"poolside/laguna-s-2.1:free","name":"Poolside: Laguna S 2.1 (free)","display_name":"Poolside: Laguna S 2.1 (free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"poolside/laguna-xs-2.1","name":"Poolside: Laguna XS 2.1","display_name":"Poolside: Laguna XS 2.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"poolside/laguna-xs-2.1:free","name":"Poolside: Laguna XS 2.1 (free)","display_name":"Poolside: Laguna XS 2.1 (free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"prism-ml/ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","display_name":"PrismML: Ternary Bonsai 2 27B","type":"chat","reasoning":{"supported":true,"default":true,"effort":"xhigh"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","medium","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","medium","xhigh"],"effort":"xhigh"}}},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","display_name":"Qwen2.5 72B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","display_name":"Qwen: Qwen2.5 7B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":29491},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","display_name":"Qwen2.5 Coder 32B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":29491},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen-plus","name":"Qwen: Qwen-Plus","display_name":"Qwen: Qwen-Plus","type":"chat","reasoning":{"supported":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","display_name":"Qwen: Qwen2.5 VL 72B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":115200},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","display_name":"Qwen: Qwen3 14B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":40960,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","display_name":"Qwen: Qwen3 235B A22B Instruct 2507","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","display_name":"Qwen: Qwen3 235B A22B Thinking 2507","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","display_name":"Qwen: Qwen3 30B A3B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":40960,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","display_name":"Qwen: Qwen3 30B A3B Instruct 2507","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","display_name":"Qwen: Qwen3 32B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":40960,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","display_name":"Qwen: Qwen3 Coder 480B A35B","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","display_name":"Qwen: Qwen3 Coder 30B A3B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","display_name":"Qwen: Qwen3 Coder Flash","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","display_name":"Qwen: Qwen3 Coder Next","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","display_name":"Qwen: Qwen3 Next 80B A3B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","display_name":"Qwen: Qwen3 Next 80B A3B Thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","display_name":"Qwen: Qwen3 VL 235B A22B Instruct","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","display_name":"Qwen: Qwen3 VL 30B A3B Instruct","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","display_name":"Qwen: Qwen3 VL 30B A3B Thinking","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","display_name":"Qwen: Qwen3 VL 8B Instruct","type":"chat","reasoning":{"supported":false},"temperature":true,"tool_call":true,"modalities":{"input":["image","text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","display_name":"Qwen: Qwen3.5-122B-A10B","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","display_name":"Qwen: Qwen3.5-27B","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":81920},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","display_name":"Qwen: Qwen3.5-35B-A3B","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","display_name":"Qwen: Qwen3.5 397B A17B","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","display_name":"Qwen: Qwen3.5-9B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":256000,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","display_name":"Qwen: Qwen3.5-Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","display_name":"Qwen: Qwen3.5 Plus 2026-02-15","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","display_name":"Qwen: Qwen3.5 Plus 2026-04-20","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","display_name":"Qwen: Qwen3.6 27B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","display_name":"Qwen: Qwen3.6 35B A3B","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","display_name":"Qwen: Qwen3.6 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","display_name":"Qwen: Qwen3.6 Plus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.7-flash","name":"Qwen: Qwen3.7 Flash","display_name":"Qwen: Qwen3.7 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.7-max","name":"Qwen: Qwen3.7 Max","display_name":"Qwen: Qwen3.7 Max","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.7-plus","name":"Qwen: Qwen3.7 Plus","display_name":"Qwen: Qwen3.7 Plus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.7-plus:batch","name":"Qwen: Qwen3.7 Plus (batch)","display_name":"Qwen: Qwen3.7 Plus (batch)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","display_name":"Qwen: Qwen3.8 2.4T A95B","type":"chat","reasoning":{"supported":true,"default":true,"effort":"xhigh"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","xhigh"],"default_enabled":true,"mode":"effort","effort":"xhigh"}}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","display_name":"Qwen: Qwen3.8 27B","type":"chat","reasoning":{"supported":true,"default":true,"effort":"xhigh"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","xhigh"],"effort":"xhigh"}}},{"id":"qwen/qwen3.8-flash","name":"Qwen: Qwen3.8 Flash","display_name":"Qwen: Qwen3.8 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"qwen/qwen3.8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","display_name":"Qwen: Qwen3.8 Max (0902)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"xhigh"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high","xhigh"],"effort":"xhigh"}}},{"id":"qwen/qwen3.8-max-prime","name":"Qwen: Qwen3.8 Max Prime","display_name":"Qwen: Qwen3.8 Max Prime","type":"chat","reasoning":{"supported":true,"default":true,"effort":"xhigh"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["minimal","low","medium","high","xhigh"],"effort":"xhigh"}}},{"id":"qwen/qwen3.8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","display_name":"Qwen: Qwen3.8 Omni Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","audio","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"reflection/beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","display_name":"Reflection: Beam 1.0 501B A23B","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh","max"],"effort":"max"}}},{"id":"rekaai/reka-edge","name":"Reka Edge","display_name":"Reka Edge","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":16384,"output":14745},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","display_name":"Reka Flash 3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":65536,"output":58982},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","display_name":"Relace: Relace Apply 3","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":256000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"relace/relace-search","name":"Relace: Relace Search","display_name":"Relace: Relace Search","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":256000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"sakana/fugu-max","name":"Sakana: Fugu Max","display_name":"Sakana: Fugu Max","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["high","xhigh","max"],"effort":"high"}}},{"id":"sakana/fugu-ultra","name":"Sakana: Fugu Ultra","display_name":"Sakana: Fugu Ultra","type":"chat","reasoning":{"supported":true,"default":true,"effort":"xhigh"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["high","xhigh","max"],"effort":"xhigh"}}},{"id":"sakana/fugu-ultra-v2","name":"Sakana: Fugu Ultra v2","display_name":"Sakana: Fugu Ultra v2","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"xhigh"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["high","xhigh","max"],"effort":"xhigh"}}},{"id":"sakana/sakana-namazu","name":"Sakana: Sakana Namazu","display_name":"Sakana: Sakana Namazu","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","high"],"effort":"high"}}},{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","display_name":"Sao10K: Llama 3 8B Lunaris","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":7372},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","display_name":"Sao10K: Llama 3.1 Euryale 70B v2.2","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"sao10k/l3.3-euryale-70b","name":"Sao10K: Llama 3.3 Euryale 70B","display_name":"Sao10K: Llama 3.3 Euryale 70B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"scaledown/extract","name":"ScaleDown: Extract","display_name":"ScaleDown: Extract","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":900000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"scaledown/summarize","name":"ScaleDown: Summarize","display_name":"ScaleDown: Summarize","type":"chat","attachment":true,"reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":4000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"stepfun/step-3.5-flash","name":"StepFun: Step 3.5 Flash","display_name":"StepFun: Step 3.5 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort_options":[]}}},{"id":"stepfun/step-3.7-flash","name":"StepFun: Step 3.7 Flash","display_name":"StepFun: Step 3.7 Flash","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":256000,"output":230400},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"stepfun/step-5-preview","name":"StepFun: Step 5 Preview","display_name":"StepFun: Step 5 Preview","type":"chat","reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high"],"effort":"medium"}}},{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","display_name":"Tencent: Hunyuan A13B Instruct","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"tencent/hy-mt2-1.8b","name":"Tencent: Hy-MT2-1.8B","display_name":"Tencent: Hy-MT2-1.8B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"tencent/hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","display_name":"Tencent: Hy-MT2-30B-A3B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"tencent/hy-mt2-7b","name":"Tencent: Hy-MT2-7B","display_name":"Tencent: Hy-MT2-7B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"tencent/hy3","name":"Tencent: Hy3","display_name":"Tencent: Hy3","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","high"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"tencent/hy3-preview","name":"Tencent: Hy3 preview","display_name":"Tencent: Hy3 preview","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","high"],"effort":"high"}}},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 preview","display_name":"Tencent: Hy4 preview","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","high"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","display_name":"TheDrummer: Cydonia 24B V4.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","display_name":"TheDrummer: Skyfall 36B V2","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":29491},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","display_name":"TheDrummer: UnslopNemo 12B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1024000,"output":819200},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"thinkingmachines/inkling","name":"Thinking Machines: Inkling","display_name":"Thinking Machines: Inkling","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"modalities":{"input":["text","image","audio"],"output":["text"]},"limit":{"context":524288,"output":471859},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high","max"],"effort":"high"}}},{"id":"thinkingmachines/inkling-small","name":"Thinking Machines: Inkling Small","display_name":"Thinking Machines: Inkling Small","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"modalities":{"input":["text","image","audio"],"output":["text"]},"limit":{"context":524288,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high","max"],"effort":"high"}}},{"id":"thinkingmachines/inkling-small:free","name":"Thinking Machines: Inkling Small (free)","display_name":"Thinking Machines: Inkling Small (free)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"modalities":{"input":["text","image","audio"],"output":["text"]},"limit":{"context":1048576,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high","max"],"effort":"high"}}},{"id":"thinkingmachines/inkling:free","name":"Thinking Machines: Inkling (free)","display_name":"Thinking Machines: Inkling (free)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"modalities":{"input":["text","image","audio"],"output":["text"]},"limit":{"context":1048576,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","minimal","low","medium","high","max"],"effort":"high"}}},{"id":"typesafe/jev-router","name":"TypeSafe: Jev Router","display_name":"TypeSafe: Jev Router","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["audio","image","text","video"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"unbiased/pareto-26.10","name":"Pareto 26.10","display_name":"Pareto 26.10","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"unbiased/pareto-26.9","name":"Pareto 26.9","display_name":"Pareto 26.9","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":262144,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","display_name":"ReMM SLERP 13B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":6144,"output":5529},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"upstage/solar-mini4","name":"Upstage: Solar Mini 4","display_name":"Upstage: Solar Mini 4","type":"chat","reasoning":{"supported":true,"default":false,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":524288,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","minimal","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"upstage/solar-pro-3","name":"Upstage: Solar Pro 3","display_name":"Upstage: Solar Pro 3","type":"chat","reasoning":{"supported":true,"default":false,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","minimal","low","medium","high"],"effort":"medium"}}},{"id":"upstage/solar-pro4","name":"Upstage: Solar Pro 4","display_name":"Upstage: Solar Pro 4","type":"chat","reasoning":{"supported":true,"default":false,"effort":"medium"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":524288,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort_options":["none","minimal","low","medium","high","xhigh","max"],"effort":"medium"}}},{"id":"writer/palmyra-x5","name":"Writer: Palmyra X5","display_name":"Writer: Palmyra X5","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1040000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"x-ai/grok-4.20","name":"SpaceXAI: Grok 4.20","display_name":"SpaceXAI: Grok 4.20","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":2000000,"output":1800000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"effort_options":[]}}},{"id":"x-ai/grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","display_name":"SpaceXAI: Grok 4.20 Multi-Agent","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"medium"},"tool_call":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":2000000,"output":1800000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh"],"effort":"medium"}}},{"id":"x-ai/grok-4.3","name":"SpaceXAI: Grok 4.3","display_name":"SpaceXAI: Grok 4.3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"low"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":900000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","low","medium","high"],"default_enabled":true,"mode":"effort","effort":"low"}}},{"id":"x-ai/grok-4.3:batch","name":"SpaceXAI: Grok 4.3 (batch)","display_name":"SpaceXAI: Grok 4.3 (batch)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"low"},"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":900000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["none","low","medium","high"],"effort":"low"}}},{"id":"x-ai/grok-4.5","name":"SpaceXAI: Grok 4.5","display_name":"SpaceXAI: Grok 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":450000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","high"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"x-ai/grok-4.6","name":"SpaceXAI: Grok 4.6","display_name":"SpaceXAI: Grok 4.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":450000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","medium","high","xhigh"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"x-ai/grok-4.7","name":"SpaceXAI: Grok 4.7","display_name":"SpaceXAI: Grok 4.7","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":450000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","medium","high","xhigh"],"effort":"high"}}},{"id":"x-ai/grok-build-0.1","name":"SpaceXAI: Grok Build 0.1","display_name":"SpaceXAI: Grok Build 0.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"reasoning_options":[],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":256000,"output":230400},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true,"mode":"fixed"}}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","display_name":"Xiaomi: MiMo-V2.5","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","audio","image","video"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","display_name":"Xiaomi: MiMo-V2.5-Pro","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","display_name":"Xiaomi: MiMo-V2.6-Flash","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"xiaomi/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","display_name":"Xiaomi: MiMo-V2.6-Pro","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","display_name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"xingchen-agi/xing4.0-29b-a4b:free","name":"XingChen: Xing4.0 29B A4B (free)","display_name":"XingChen: Xing4.0 29B A4B (free)","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":235929},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"z-ai/glm-4.5","name":"Z.ai: GLM 4.5","display_name":"Z.ai: GLM 4.5","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":98304},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","display_name":"Z.ai: GLM 4.5 Air","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":98304},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"z-ai/glm-4.5v","name":"Z.ai: GLM 4.5V","display_name":"Z.ai: GLM 4.5V","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":65536,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","display_name":"Z.ai: GLM 4.6","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":202752,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"z-ai/glm-4.6v","name":"Z.ai: GLM 4.6V","display_name":"Z.ai: GLM 4.6V","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","display_name":"Z.ai: GLM 4.7","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"z-ai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","display_name":"Z.ai: GLM 4.7 Flash","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":117964},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","display_name":"Z.ai: GLM 5","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":202752,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"effort_options":[],"default_enabled":true}}},{"id":"z-ai/glm-5-turbo","name":"Z.ai: GLM 5 Turbo","display_name":"Z.ai: GLM 5 Turbo","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":202752,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","display_name":"Z.ai: GLM 5.1","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":200000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":[],"default_enabled":true}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","display_name":"Z.ai: GLM 5.2","type":"chat","reasoning":{"supported":true,"default":true,"effort":"high"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","xhigh"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["none","high","xhigh"],"default_enabled":true,"mode":"effort","effort":"high"}}},{"id":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","display_name":"Z.ai: GLM 5.3","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","high","max"],"default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","display_name":"Z.ai: GLM 5.3 Flash","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"effort_options":["low","high","max"],"default_enabled":true,"mode":"effort","effort":"max"}}},{"id":"z-ai/glm-5.3-flash:batch","name":"Z.ai: GLM 5.3 Flash (batch)","display_name":"Z.ai: GLM 5.3 Flash (batch)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"max"}}},{"id":"z-ai/glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","display_name":"Z.ai: GLM 5.3 FlashX","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"max"}}},{"id":"z-ai/glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","display_name":"Z.ai: GLM 5.3 Prime","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"max"}}},{"id":"z-ai/glm-5.3:batch","name":"Z.ai: GLM 5.3 (batch)","display_name":"Z.ai: GLM 5.3 (batch)","type":"chat","reasoning":{"supported":true,"default":true,"effort":"max"},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort_options":["low","high","max"],"effort":"max"}}},{"id":"z-ai/glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","display_name":"Z.ai: GLM 5V Turbo","type":"chat","reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"reasoning_options":[{"type":"toggle"}],"modalities":{"input":["image","text","video"],"output":["text"]},"limit":{"context":202752,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"effort_options":[]}}}],"metadata":{"source":"public-provider-conf"}},"jiekou":{"id":"jiekou","name":"Jiekou","display_name":"Jiekou","updated_at":"2026-10-18T20:13:14.331Z","models":[{"id":"claude-opus-5-5","name":"claude-opus-5-5","display_name":"claude-opus-5-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":40000,"outputPerM":200000},"source":"public-provider-conf"},"vision":true},{"id":"claude-fable-5-1","name":"claude-fable-5-1","display_name":"claude-fable-5-1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":100000,"outputPerM":500000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"claude-fable-5","name":"claude-fable-5","display_name":"claude-fable-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":100000,"outputPerM":500000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","display_name":"DeepSeek V4.1 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"endpoints":["chat/completions","anthropic","responses"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":3000,"outputPerM":12000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5.3-flash","name":"GLM 5.3 Flash","display_name":"GLM 5.3 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","endpoints":["chat/completions","anthropic","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1500,"outputPerM":5000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5.3","name":"GLM 5.3","display_name":"GLM 5.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"description":"GLM-5.3 is Z.ai’s latest flagship model, delivering comprehensive advancements in complex software engineering and agent capabilities. It uses the same base model as GLM-5.2, with all improvements driven by post-training.","endpoints":["chat/completions","anthropic","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":14000,"outputPerM":44000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","display_name":"DeepSeek V4 Pro 0813","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"endpoints":["chat/completions","responses","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":13200,"outputPerM":39600},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-7","name":"claude-opus-4-7","display_name":"claude-opus-4-7","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":47500,"outputPerM":237500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"qwen/qwen3.8-flash","name":"Qwen3.8 Flash","display_name":"Qwen3.8 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"description":"Qwen3.8-Flash is Alibaba's multimodal MoE model and an early preview of the Qwen4 architecture: 125B total parameters with only 6B activated per token, plus a 51B N-gram embedding, built on GDN + QSA hybrid attention. It accepts text, image and video input across a 1M-token context and emits up to 131K tokens, with thinking mode on by default and switchable off. Built for coding, agentic workflows, visual\nand long-document understanding, and long-video analysis at a fraction of the cost of comparable frontier models.","endpoints":["chat/completions","anthropic","responses"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":1500,"outputPerM":4700},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","display_name":"DeepSeek V4 Flash Vision Exp","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731(opens in new tab) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.\n\nIt is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.","endpoints":["chat/completions","anthropic","responses"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":4400,"outputPerM":13200},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-flash-0731","name":"Deepseek V4 Flash 0731","display_name":"Deepseek V4 Flash 0731","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.","endpoints":["chat/completions","anthropic","responses"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":4400,"outputPerM":13200},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-4-argon","name":"gemini-4-argon","display_name":"gemini-4-argon","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":100000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6.1-sol","name":"gpt-6.1-sol","display_name":"gpt-6.1-sol","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":100000},"source":"public-provider-conf"},"vision":true},{"id":"claude-sonnet-5-5","name":"claude-sonnet-5-5","display_name":"claude-sonnet-5-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":100000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6-luna","name":"gpt-6-luna","display_name":"gpt-6-luna","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1000,"outputPerM":5000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6-sol","name":"gpt-6-sol","display_name":"gpt-6-sol","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":100000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-6-astra","name":"gpt-6-astra","display_name":"gpt-6-astra","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":95000,"outputPerM":475000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.8-flash","name":"gemini-3.8-flash","display_name":"gemini-3.8-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":7500,"outputPerM":37500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","display_name":"Qwen3.8 27B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"endpoints":["chat/completions","anthropic","responses"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":4200,"outputPerM":30000},"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","display_name":"Qwen3.8 2.4T A95B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.Text-only.","endpoints":["chat/completions","responses"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.7-flash","name":"gemini-3.7-flash","display_name":"gemini-3.7-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":7500,"outputPerM":37500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"claude-opus-5","name":"claude-opus-5","display_name":"claude-opus-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":50000,"outputPerM":250000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.6-flash","name":"gemini-3.6-flash","display_name":"gemini-3.6-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":7500,"outputPerM":37500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"moonshotai/kimi-k3","name":"Kimi K3","display_name":"Kimi K3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Kimi K3 is Kimi’s most capable model to date, with 2.8 trillion parameters. Built on Kimi Delta Attention, a hybrid linear attention mechanism, and Attention Residuals, it offers native visual understanding and a 1M-token context window for frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning.","endpoints":["chat/completions","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":30000,"outputPerM":150000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.6-terra-es","name":"gpt-5.6-terra-es","display_name":"gpt-5.6-terra-es","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":3720000,"output":128000},"metadata":{"endpoints":["responses","chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2000,"outputPerM":12000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.6-sol-es","name":"gpt-5.6-sol-es","display_name":"gpt-5.6-sol-es","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":372000,"output":128000},"metadata":{"endpoints":["responses","chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":4000,"outputPerM":20000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.6-terra","name":"gpt-5.6-terra","display_name":"gpt-5.6-terra","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":120000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-luna","name":"gpt-5.6-luna","display_name":"gpt-5.6-luna","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2000,"outputPerM":12000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.6-sol","name":"gpt-5.6-sol","display_name":"gpt-5.6-sol","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":40000,"outputPerM":200000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gemini-3.1-flash-lite","name":"gemini-3.1-flash-lite","display_name":"gemini-3.1-flash-lite","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2500,"outputPerM":15000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-sonnet-5","name":"claude-sonnet-5","display_name":"claude-sonnet-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":100000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5.2","name":"GLM 5.2","display_name":"GLM 5.2","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":163840},"metadata":{"description":"GLM-5.2 is Z.AI's latest flagship model, meticulously engineered for long-horizon autonomous tasks. Capable of working continuously on a single assignment for up to 8 hours, it autonomously manages the entire workflow—from initial planning and execution to iterative optimization and the delivery of production-grade results. With coding and agentic capabilities that rival leading proprietary frontier models, it excels particularly in sustained execution, complex engineering optimization, and real-world development scenarios. Its context window has been expanded from 200K to 1M tokens, making it an ideal foundational model for powering advanced autonomous agents and long-horizon coding assistants.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":14000,"outputPerM":44000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","display_name":"Kimi K2.7 Code","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":262144},"metadata":{"description":"Kimi K2.7 Code is MoonshotAI's strongest coding & agentic model — a 1T-parameter MoE (32B activated) , 256K context and interleaved thinking with multi-step tool calling. It delivers major gains on long-horizon coding tasks while cutting thinking-token usage by ~30% vs K2.6, and accepts text, image and video inputs for vision-driven development workflows.","endpoints":["chat/completions","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":9500,"outputPerM":40000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m3","name":"MiniMax M3","display_name":"MiniMax M3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131072},"metadata":{"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.","endpoints":["chat/completions","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":3000,"outputPerM":12000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"claude-opus-4-8","name":"claude-opus-4-8","display_name":"claude-opus-4-8","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":47500,"outputPerM":237500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"gpt-5.5","name":"gpt-5.5","display_name":"gpt-5.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","anthropic","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":47500,"outputPerM":285000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4.1-nano","name":"gpt-4.1-nano","display_name":"gpt-4.1-nano","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":950,"outputPerM":3800},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.5-flash","name":"gemini-3.5-flash","display_name":"gemini-3.5-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":14250,"outputPerM":85500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-3.1-pro-preview","name":"gemini-3.1-pro-preview","display_name":"gemini-3.1-pro-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":19000,"outputPerM":114000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"deepseek/deepseek-v4-flash","name":"Deepseek V4 Flash","display_name":"Deepseek V4 Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"description":"DeepSeek-V4-Flash is a lightweight model meticulously designed by DeepSeek to deliver the ultimate combination of lightning-fast response times and unmatched cost-effectiveness. Engineered with fewer parameters and significantly lower activation overhead, V4-Flash provides an exceptionally fast and economical API service. At its core, V4-Flash demonstrates outstanding reasoning capabilities that closely rival the V4-Pro model. While featuring a slightly streamlined repository of world knowledge, it remains highly capable of satisfying the demands of most application scenarios. In Agentic applications, V4-Flash performs on par with the Pro version when handling standard and fundamental tasks. As the premier choice for developers prioritizing high concurrency, low latency, and cost efficiency, DeepSeek-V4-Flash serves as the optimal solution for deploying large-scale, high-frequency, and lightweight AI workloads.","endpoints":["chat/completions","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":1400,"outputPerM":2800},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-pro","name":"Deepseek V4 Pro","display_name":"Deepseek V4 Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":393216},"metadata":{"description":"DeepSeek-V4-Pro is the next-generation flagship open-source large language model developed by DeepSeek, delivering comprehensive performance that rivals the world's premier closed-source models. Compared to its predecessor, V4-Pro achieves a breakthrough evolution in Agentic capabilities. It firmly holds the top position among open-source models in Agentic Coding, providing a high-quality, end-to-end code delivery experience that surpasses mainstream industry benchmarks (such as Sonnet 4.5). Furthermore, the model not only boasts an expansive repository of world knowledge that leads the open-source community, but it also demonstrates ultimate logical reasoning prowess in highly demanding evaluations—including mathematics, STEM, and competitive programming. In these rigorous domains, V4-Pro outperforms all publicly evaluated open-source models and matches the capabilities of global closed-source giants. As the ideal foundational model for building complex agentic workflows, professional-grade software developm","endpoints":["chat/completions","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":16000,"outputPerM":32000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","display_name":"MiniMax M2.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131100},"metadata":{"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":3000,"outputPerM":12000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","display_name":"Kimi K2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":262144},"metadata":{"description":"Kimi K2.5 is the latest flagship iteration of Moonshot AI's large language model series, representing a significant leap in multimodal and agentic capabilities. It features a native multimodal architecture supporting both visual and text inputs, alongside versatile thinking and non-thinking modes. This model maintains the substantial 256k token context window found in the K2 series but achieves new open-source state-of-the-art (SoTA) performance across general intelligence, coding, and visual understanding benchmarks. Kimi K2.5 delivers a breakthrough in frontend development, enabling the generation of fully functional, aesthetically polished interactive interfaces with complex dynamic layouts directly from natural language. Optimized for complex problem-solving, it excels in multi-step tool invocation, logical reasoning, and full-stack code synthesis.","endpoints":["chat/completions","anthropic"],"features":["serverless","reasoning","structured-outputs","function-calling"],"pricing":{"inputPerM":6000,"outputPerM":30000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","display_name":"Kimi K2 Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":100352},"metadata":{"description":"Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.Specifically designed for tool use, reasoning, and autonomous problem-solving.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":5700,"outputPerM":23000},"source":"public-provider-conf"},"vision":false},{"id":"zai-org/glm-5.1","name":"GLM-5.1","display_name":"GLM-5.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"description":"GLM-5.1 is Z.AI's latest flagship model, meticulously engineered for long-horizon autonomous tasks. Capable of working continuously on a single assignment for up to 8 hours, it autonomously manages the entire workflow—from initial planning and execution to iterative optimization and the delivery of production-grade results. While its general capabilities and coding proficiency are on par with Claude Opus 4.6, GLM-5.1 excels particularly in sustained execution, complex engineering optimization, and real-world development scenarios. This makes it the ideal foundational model for powering advanced autonomous agents and long-horizon coding assistants.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":13800,"outputPerM":44000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5v-turbo","name":"GLM-5V-Turbo","display_name":"GLM-5V-Turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"description":"GLM-5V-Turbo is Z.AI’s first multimodal coding foundation model, built for vision-based coding tasks. It can natively process multimodal inputs such as images, video, and text, while also excelling at long-horizon planning, complex coding, and action execution. Deeply optimized for agent workflows, it works seamlessly with agents such as Claude Code and OpenClaw to complete the full loop of “understand the environment → plan actions → execute tasks”.","endpoints":["chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":12000,"outputPerM":40000},"source":"public-provider-conf"},"vision":true},{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B","display_name":"ERNIE 4.5 VL 424B A47B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":123000,"output":16000},"metadata":{"description":"The ERNIE 4.5 series of open-source models adopts a Mixture-of-Experts (MoE) architecture, representing an innovative multimodal heterogeneous model structure. It achieves cross-modal knowledge fusion through a parameter-sharing mechanism while retaining dedicated parameter spaces for individual modalities. This architecture is particularly well-suited for the continuous pre-training paradigm from large language models to multimodal models, significantly enhancing multimodal understanding capabilities while maintaining or even improving performance in text-based tasks. The models are efficiently trained, inferred, and deployed using the PaddlePaddle deep learning framework. During the pre-training of large language models, the Model FLOPs Utilization (MFU) reaches 47%. Experimental results demonstrate that this series of models achieves state-of-the-art (SOTA) performance across multiple text and multimodal benchmarks, with particularly outstanding results in instruction following, world knowledge memorizatio","endpoints":["chat/completions","completions"],"features":["function-calling","reasoning","serverless"],"pricing":{"inputPerM":4200,"outputPerM":12500},"source":"public-provider-conf"},"vision":true},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","display_name":"Llama 3.1 8B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":16384,"output":16384},"metadata":{"description":"Meta's latest class of models, Llama 3.1, launched with a variety of sizes and configurations. The 8B instruct-tuned version is particularly fast and efficient. It has demonstrated strong performance in human evaluations, outperforming several leading closed-source models.","endpoints":["chat/completions","completions"],"features":["serverless"],"pricing":{"inputPerM":200,"outputPerM":500},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","display_name":"Qwen3 235B A22B Instruct 2507","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":16384},"metadata":{"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement \"thinking mode\" (<think> blocks). Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":1500,"outputPerM":8000},"source":"public-provider-conf"},"vision":false},{"id":"mistralai/mistral-nemo","name":"Mistral Nemo","display_name":"Mistral Nemo","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":60288,"output":32000},"metadata":{"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.","endpoints":["chat/completions","completions"],"features":["structured-outputs","serverless"],"pricing":{"inputPerM":400,"outputPerM":1700},"source":"public-provider-conf"},"vision":false},{"id":"claude-opus-4-8-r","name":"claude-opus-4-8-r","display_name":"claude-opus-4-8-r","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":10000,"outputPerM":50000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-opus-4-7-r","name":"claude-opus-4-7-r","display_name":"claude-opus-4-7-r","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":10000,"outputPerM":50000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-opus-4-6","name":"claude-opus-4-6","display_name":"claude-opus-4-6","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":47500,"outputPerM":237500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-4-6-r","name":"claude-opus-4-6-r","display_name":"claude-opus-4-6-r","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":10000,"outputPerM":50000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-sonnet-4-6","name":"claude-sonnet-4-6","display_name":"claude-sonnet-4-6","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Our smartest model. Best for complex agents, coding, and most advanced tasks","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":28500,"outputPerM":142500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-sonnet-4-6-r","name":"claude-sonnet-4-6-r","display_name":"claude-sonnet-4-6-r","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Our smartest model. Best for complex agents, coding, and most advanced tasks","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":6000,"outputPerM":30000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-4-5-20251101","name":"claude-opus-4-5-20251101","display_name":"claude-opus-4-5-20251101","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":65536},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":47500,"outputPerM":237500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"claude-sonnet-4-5-20250929","name":"claude-sonnet-4-5-20250929","display_name":"claude-sonnet-4-5-20250929","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":64000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":28500,"outputPerM":142500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-haiku-4-5-20251001","name":"claude-haiku-4-5-20251001","display_name":"claude-haiku-4-5-20251001","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":20000,"output":20000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":10000,"outputPerM":50000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"claude-haiku-4-5-20251001-r","name":"claude-haiku-4-5-20251001-r","display_name":"claude-haiku-4-5-20251001-r","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":64000},"metadata":{"description":"Our fastest model with near-frontier intelligence","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2000,"outputPerM":10000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"gpt-5.5-pro","name":"gpt-5.5-pro","display_name":"gpt-5.5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","reasoning","serverless"],"pricing":{"inputPerM":300000,"outputPerM":1800000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gpt-5.5-light","name":"gpt-5.5-light","display_name":"gpt-5.5-light","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2500,"outputPerM":15000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-5.4-pro","name":"gpt-5.4-pro","display_name":"gpt-5.4-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","reasoning","serverless"],"pricing":{"inputPerM":285000,"outputPerM":1710000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4","name":"gpt-5.4","display_name":"gpt-5.4","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1050000,"output":128000},"metadata":{"endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":23750,"outputPerM":142500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-mini","name":"gpt-5.4-mini","display_name":"gpt-5.4-mini","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"description":"Our strongest mini model yet for coding, computer use, and subagents","endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":7125,"outputPerM":42750},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.4-nano","name":"gpt-5.4-nano","display_name":"gpt-5.4-nano","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"description":"Our cheapest GPT-5.4-class model for simple high-volume tasks","endpoints":["responses","chat/completions","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1900,"outputPerM":11875},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.3-codex","name":"gpt-5.3-codex","display_name":"gpt-5.3-codex","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":16625,"outputPerM":133000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-pro","name":"gpt-5.2-pro","display_name":"gpt-5.2-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":199500,"outputPerM":1596000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2-codex","name":"gpt-5.2-codex","display_name":"gpt-5.2-codex","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":17500,"outputPerM":140000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.2","name":"gpt-5.2","display_name":"gpt-5.2","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":16625,"outputPerM":133000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-max","name":"gpt-5.1-codex-max","display_name":"gpt-5.1-codex-max","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11875,"outputPerM":95000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex","name":"gpt-5.1-codex","display_name":"gpt-5.1-codex","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11875,"outputPerM":95000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1-codex-mini","name":"gpt-5.1-codex-mini","display_name":"gpt-5.1-codex-mini","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2375,"outputPerM":19000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5.1","name":"gpt-5.1","display_name":"gpt-5.1","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11875,"outputPerM":95000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-pro","name":"gpt-5-pro","display_name":"gpt-5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":272000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":142500,"outputPerM":1140000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-codex","name":"gpt-5-codex","display_name":"gpt-5-codex","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11875,"outputPerM":95000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5","name":"gpt-5","display_name":"gpt-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11875,"outputPerM":95000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-mini","name":"gpt-5-mini","display_name":"gpt-5-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2375,"outputPerM":19000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-5-nano","name":"gpt-5-nano","display_name":"gpt-5-nano","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":400000,"output":128000},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":475,"outputPerM":3800},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"gpt-4.1","name":"gpt-4.1","display_name":"gpt-4.1","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":20000,"outputPerM":80000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-4.1-mini","name":"gpt-4.1-mini","display_name":"gpt-4.1-mini","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1047576,"output":32768},"metadata":{"endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":4000,"outputPerM":16000},"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-oss-20b","name":"OpenAI: GPT OSS 20B","display_name":"OpenAI: GPT OSS 20B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":32768},"metadata":{"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.","endpoints":["chat/completions","completions"],"features":["structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":500,"outputPerM":2000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"o3","name":"o3","display_name":"o3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"description":"chatgpt-o3","endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":95000,"outputPerM":380000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"o3-mini","name":"o3-mini","display_name":"o3-mini","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":100000},"metadata":{"description":"chatgpt-o3-mini","endpoints":["chat/completions","responses","compact"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":10450,"outputPerM":41800},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-oss-120b","name":"OpenAI GPT OSS 120B","display_name":"OpenAI GPT OSS 120B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":131072},"metadata":{"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1000,"outputPerM":5000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-flash-preview","name":"gemini-3-flash-preview","display_name":"gemini-3-flash-preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":4750,"outputPerM":28500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro","name":"gemini-2.5-pro","display_name":"gemini-2.5-pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65535},"metadata":{"endpoints":["chat/completions","gemini"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11875,"outputPerM":95000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-pro-preview-06-05","name":"gemini-2.5-pro-preview-06-05","display_name":"gemini-2.5-pro-preview-06-05","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":200000},"metadata":{"endpoints":["chat/completions","gemini"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11875,"outputPerM":95000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-preview-05-20","name":"gemini-2.5-flash-preview-05-20","display_name":"gemini-2.5-flash-preview-05-20","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":200000},"metadata":{"endpoints":["chat/completions","gemini"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1425,"outputPerM":33250},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"grok-4.20-multi-agent-0309","name":"grok-4.20-multi-agent-0309","display_name":"grok-4.20-multi-agent-0309","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":2000000,"output":2000000},"metadata":{"endpoints":["chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":19000,"outputPerM":57000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-2.5-flash","name":"gemini-2.5-flash","display_name":"gemini-2.5-flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65535},"metadata":{"endpoints":["chat/completions","gemini"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2850,"outputPerM":23750},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-lite","name":"gemini-2.5-flash-lite","display_name":"gemini-2.5-flash-lite","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65535},"metadata":{"endpoints":["chat/completions","gemini"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":950,"outputPerM":3800},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B","display_name":"Gemma 3 27B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":32768,"output":32768},"metadata":{"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 32k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs. Gemma 3 27B is Google's latest open source model, successor to Gemma.","endpoints":["chat/completions","completions"],"features":["structured-outputs","serverless"],"pricing":{"inputPerM":1190,"outputPerM":2000},"source":"public-provider-conf"},"vision":true},{"id":"google/gemma-3-12b-it","name":"Gemma3 12B","display_name":"Gemma3 12B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":8192},"metadata":{"endpoints":["chat/completions","completions"],"features":["structured-outputs","serverless"],"pricing":{"inputPerM":500,"outputPerM":1000},"source":"public-provider-conf"},"vision":true},{"id":"grok-4-0709","name":"grok-4-0709","display_name":"grok-4-0709","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":256000,"output":256000},"metadata":{"endpoints":["chat/completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":28500,"outputPerM":142500},"source":"public-provider-conf"},"vision":true},{"id":"grok-4.20-0309-reasoning","name":"grok-4.20-0309-reasoning","display_name":"grok-4.20-0309-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":2000000,"output":2000000},"metadata":{"description":"Grok 4.20 is our newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","endpoints":["chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":19000,"outputPerM":57000},"source":"public-provider-conf"},"vision":true},{"id":"grok-4.20-0309-non-reasoning","name":"grok-4.20-0309-non-reasoning","display_name":"grok-4.20-0309-non-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":2000000,"output":2000000},"metadata":{"description":"Grok 4.20 is our newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","endpoints":["chat/completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":19000,"outputPerM":57000},"source":"public-provider-conf"},"vision":true},{"id":"grok-4.3","name":"grok-4.3","display_name":"grok-4.3","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":1000000},"metadata":{"endpoints":["chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":12500,"outputPerM":25000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4-1-fast-reasoning","name":"grok-4-1-fast-reasoning","display_name":"grok-4-1-fast-reasoning","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":2000000,"output":2000000},"metadata":{"endpoints":["chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1900,"outputPerM":4750},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4-1-fast-non-reasoning","name":"grok-4-1-fast-non-reasoning","display_name":"grok-4-1-fast-non-reasoning","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":2000000,"output":2000000},"metadata":{"endpoints":["chat/completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":1900,"outputPerM":4750},"source":"public-provider-conf"},"vision":true},{"id":"grok-code-fast-1","name":"grok-code-fast-1","display_name":"grok-code-fast-1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":256000,"output":256000},"metadata":{"endpoints":["chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1900,"outputPerM":14250},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528","display_name":"DeepSeek R1 0528","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":32768},"metadata":{"description":"DeepSeek R1 0528 is the latest open-source model released by the DeepSeek team, featuring impressive reasoning capabilities, particularly achieving performance comparable to OpenAI's o1 model in mathematics, coding, and reasoning tasks.","endpoints":["chat/completions","completions","batch-api"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":7000,"outputPerM":25000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"deepseek/deepseek-v3-0324","name":"DeepSeek V3 0324","display_name":"DeepSeek V3 0324","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":163840},"metadata":{"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.","endpoints":["chat/completions","completions","anthropic"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":2800,"outputPerM":11400},"source":"public-provider-conf"},"vision":false},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","display_name":"DeepSeek V3.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":163840,"output":32768},"metadata":{"description":"DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode.DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens.","endpoints":["chat/completions","completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":2700,"outputPerM":10000},"source":"public-provider-conf"},"vision":false},{"id":"deepseek/deepseek-ocr-2","name":"DeepSeek-OCR 2","display_name":"DeepSeek-OCR 2","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"DeepSeek-OCR 2 is a multimodal document recognition model released by DeepSeek AI, serving as an upgrade to DeepSeek-OCR. By introducing the DeepEncoder V2 architecture, it achieves a paradigm shift in visual encoding from \"fixed scanning\" to \"semantic reasoning.\" The model replaces the original CLIP encoder with a lightweight language model (Qwen2-0.5B) and incorporates a causal flow query mechanism, while retaining the DeepSeek-3B-MoE decoder. The model requires only 256 to 1120 visual tokens to cover complex document pages. On the OmniDocBench v1.5 benchmark, it achieves an overall score of 91.09%, a 3.73% improvement over its predecessor, with reading order recognition edit distance reduced from 0.085 to 0.057.","endpoints":["chat/completions"],"features":["serverless"],"pricing":{"inputPerM":300,"outputPerM":300},"source":"public-provider-conf"},"vision":true},{"id":"baidu/ernie-4.5-300b-a47b-paddle","name":"ERNIE 4.5 300B A47B","display_name":"ERNIE 4.5 300B A47B","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":123000,"output":12000},"metadata":{"description":"The ERNIE 4.5 series of open-source models adopts a Mixture-of-Experts (MoE) architecture, representing an innovative multimodal heterogeneous model structure. It achieves cross-modal knowledge fusion through a parameter-sharing mechanism while retaining dedicated parameter spaces for individual modalities. This architecture is particularly well-suited for the continuous pre-training paradigm from large language models to multimodal models, significantly enhancing multimodal understanding capabilities while maintaining or even improving performance in text-based tasks. The models are efficiently trained, inferred, and deployed using the PaddlePaddle deep learning framework. During the pre-training of large language models, the Model FLOPs Utilization (MFU) reaches 47%. Experimental results demonstrate that this series of models achieves state-of-the-art (SOTA) performance across multiple text and multimodal benchmarks, with particularly outstanding results in instruction following, world knowledge memorizatio","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":2800,"outputPerM":11000},"source":"public-provider-conf"},"vision":false},{"id":"zai-org/glm-4.5v","name":"GLM 4.5V","display_name":"GLM 4.5V","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":65536,"output":16384},"metadata":{"description":"Z.ai's GLM-4.5V sets a new standard in visual reasoning, achieving SOTA performance across 42 benchmarks among open-source models. Beyond benchmarks, it excels in real-world applications through hybrid training, enabling comprehensive visual understanding—from image/video analysis and GUI interaction to complex document processing and precise visual grounding.  In China's GeoGuessr challenge, GLM-4.5V surpassed 99% of 21,000 human players within 16 hours, reaching 66th place in a week. Built on the GLM-4.5-Air foundation and inheriting GLM-4.1V-Thinking's approach, it leverages a 106B-parameter MoE architecture for scalable, efficient performance. This model bridges advanced AI research with practical deployment, delivering unmatched visual intelligence","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":6000,"outputPerM":18000},"source":"public-provider-conf"},"vision":true},{"id":"zai-org/glm-4.5","name":"GLM-4.5","display_name":"GLM-4.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":98304},"metadata":{"description":"GLM-4.5 Series Models are foundation models specifically engineered for intelligent agents. The flagship GLM-4.5 integrates 355 billion total parameters (32 billion active), unifying reasoning, coding, and agent capabilities to address complex application demands. As a hybrid reasoning system, it offers dual operational modes: - Thinking Mode: Enables complex reasoning, tool invocation, and strategic planning - Non-Thinking Mode: Delivers low-latency responses for real-time interactions This architecture bridges high-performance AI with adaptive functionality for dynamic agent environments.","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":6000,"outputPerM":22000},"source":"public-provider-conf"},"vision":false},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","display_name":"Kimi K2.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":262144},"metadata":{"description":"Kimi K2.5 is the latest flagship iteration of Moonshot AI's large language model series, representing a significant leap in multimodal and agentic capabilities. It features a native multimodal architecture supporting both visual and text inputs, alongside versatile thinking and non-thinking modes. This model maintains the substantial 256k token context window found in the K2 series but achieves new open-source state-of-the-art (SoTA) performance across general intelligence, coding, and visual understanding benchmarks. Kimi K2.5 delivers a breakthrough in frontend development, enabling the generation of fully functional, aesthetically polished interactive interfaces with complex dynamic layouts directly from natural language. Optimized for complex problem-solving, it excels in multi-step tool invocation, logical reasoning, and full-stack code synthesis.","endpoints":["chat/completions","anthropic"],"features":["serverless","reasoning","structured-outputs","function-calling"],"pricing":{"inputPerM":8000,"outputPerM":34000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-4.7","name":"GLM-4.7","display_name":"GLM-4.7","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"description":"GLM-4.7 is Z.AI's latest flagship model, with major upgrades focused on advanced coding capabilities and more reliable multi-step reasoning and execution. It shows clear gains in complex agent workflows, while delivering a more natural conversational experience and stronger front-end design sensibility.","endpoints":["chat/completions","anthropic","completion"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":6000,"outputPerM":22000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","display_name":"GLM-4.7-Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":200000,"output":128000},"metadata":{"description":"GLM-4.7-Flash, a state-of-the-art model in the 30B class, delivers a compelling balance of high performance and efficiency. Tailored for Agentic Coding, it strengthens coding proficiency, long-horizon planning, and tool synergy, securing top-tier results on public benchmarks among similarly sized open-source models. It excels in complex agent tasks with superior instruction following for tool use, while significantly elevating the frontend aesthetics and completion efficiency of long-range workflows in Artifacts and Agentic Coding.","endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":700,"outputPerM":4000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-5","name":"GLM-5","display_name":"GLM-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"description":"GLM-5 is an open-source foundation model engineered for complex system engineering and long-horizon Agent tasks, delivering reliable productivity for top-tier programmers. Transcending the boundary from \"writing code\" to \"building systems,\" it moves beyond traditional snippet generation to offer senior-architect-level planning and execution capabilities. By rejecting the \"frontend-heavy, logic-light\" approach, GLM-5 demonstrates exceptional reasoning and self-healing abilities in backend refactoring, complex algorithm implementation, and deep debugging—autonomously analyzing logs and iteratively fixing persistent bugs until the system runs. As the first open-source model featuring Opus-class style and system engineering depth, GLM-5 provides extreme logic density alongside the freedom of local deployment and high cost-effectiveness, making it the ideal choice for large-scale backend development and automated Agent construction.","endpoints":["chat/completions","anthropic","completion"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":10000,"outputPerM":32000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"zai-org/glm-5-turbo","name":"GLM-5-Turbo","display_name":"GLM-5-Turbo","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":202800,"output":131072},"metadata":{"description":"GLM-5 is an open-source foundation model engineered for complex system engineering and long-horizon Agent tasks, delivering reliable productivity for top-tier programmers. Transcending the boundary from \"writing code\" to \"building systems,\" it moves beyond traditional snippet generation to offer senior-architect-level planning and execution capabilities. By rejecting the \"frontend-heavy, logic-light\" approach, GLM-5 demonstrates exceptional reasoning and self-healing abilities in backend refactoring, complex algorithm implementation, and deep debugging—autonomously analyzing logs and iteratively fixing persistent bugs until the system runs. As the first open-source model featuring Opus-class style and system engineering depth, GLM-5 provides extreme logic density alongside the freedom of local deployment and high cost-effectiveness, making it the ideal choice for large-scale backend development and automated Agent construction.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":12000,"outputPerM":40000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"zai-org/glm-ocr","name":"GLM-OCR","display_name":"GLM-OCR","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":32000,"output":32000},"metadata":{"description":"GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, achieving SOTA performance with a score of 94.62 on OmniDocBench V1.5. Optimized for real-world business scenarios, it delivers high-precision recognition for handwritten text, stamps, and code documentation. The model supports directly rendering complex tables into HTML code and extracting structured data from IDs and receipts into standard JSON format, enabling high-accuracy document parsing with minimal resource consumption.","endpoints":["chat/completions"],"features":["serverless","structured-outputs"],"pricing":{"inputPerM":300,"outputPerM":300},"source":"public-provider-conf"},"vision":true},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","display_name":"Kimi K2 0905","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":100352},"metadata":{"description":"Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.","endpoints":["chat/completions","completions","anthropic"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":6000,"outputPerM":25000},"source":"public-provider-conf"},"vision":false},{"id":"Sao10K/L3-8B-Stheno-v3.2","name":"L3 8B Stheno V3.2","display_name":"L3 8B Stheno V3.2","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Sao10K/L3-8B-Stheno-v3.2 is a highly skilled actor that excels at fully immersing itself in any role assigned.","endpoints":["chat/completions","completions"],"features":["function-calling","serverless"],"pricing":{"inputPerM":500,"outputPerM":500},"source":"public-provider-conf"},"vision":false},{"id":"sao10k/l3-70b-euryale-v2.1","name":"L3 70B Euryale V2.1","display_name":"L3 70B Euryale V2.1","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"The uncensored llama3 model is a powerhouse of creativity, excelling in both roleplay and story writing. It offers a liberating experience during roleplays, free from any restrictions. This model stands out for its immense creativity, boasting a vast array of unique ideas and plots, truly a treasure trove for those seeking originality. Its unrestricted nature during roleplays allows for the full breadth of imagination to unfold, akin to an enhanced, big-brained version of Stheno. Perfect for creative minds seeking a boundless platform for their imaginative expressions, the uncensored llama3 model is an ideal choice","endpoints":["chat/completions","completions"],"features":["function-calling","serverless"],"pricing":{"inputPerM":14800,"outputPerM":14800},"source":"public-provider-conf"},"vision":false},{"id":"sao10k/l31-70b-euryale-v2.2","name":"L31 70B Euryale V2.2","display_name":"L31 70B Euryale V2.2","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.","endpoints":["chat/completions","completions"],"features":["function-calling","serverless"],"pricing":{"inputPerM":14800,"outputPerM":14800},"source":"public-provider-conf"},"vision":false},{"id":"inclusionai/ling-2.6-flash","name":"Ling-2.6-flash","display_name":"Ling-2.6-flash","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":32768},"metadata":{"endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs"],"pricing":{"inputPerM":1000,"outputPerM":3000},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","display_name":"Llama 3.3 70B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":120000},"metadata":{"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.  Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.","endpoints":["chat/completions","completions"],"features":["function-calling","serverless"],"pricing":{"inputPerM":1300,"outputPerM":3900},"source":"public-provider-conf"},"vision":false},{"id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick Instruct","display_name":"Llama 4 Maverick Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1048576,"output":1048576},"metadata":{"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.  Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.","endpoints":["chat/completions","completions"],"features":["function-calling","serverless"],"pricing":{"inputPerM":1700,"outputPerM":8500},"source":"public-provider-conf"},"vision":true},{"id":"meta-llama/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout Instruct","display_name":"Llama 4 Scout Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":131072,"output":131072},"metadata":{"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.  Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.","endpoints":["chat/completions","completions"],"features":["function-calling","serverless"],"pricing":{"inputPerM":1000,"outputPerM":5000},"source":"public-provider-conf"},"vision":true},{"id":"minimaxai/minimax-m1-80k","name":"MiniMax M1","display_name":"MiniMax M1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1000000,"output":40000},"metadata":{"description":"MiniMax-M1: The World's First Open-Weight, Large-Scale Hybrid Attention Inference Model  MiniMax-M1 adopts a Mixture of Experts (MoE) architecture and integrates the Flash Attention mechanism. The model contains a total of 456 billion parameters, with 45.9 billion parameters activated per token.  Natively, the M1 model supports a context length of 1 million tokens—8 times that of DeepSeek R1. Additionally, by combining the CISPO algorithm with an efficient hybrid attention design for reinforcement learning training, MiniMax-M1 achieves industry-leading performance in long-context reasoning and real-world software engineering scenarios.","endpoints":["chat/completions"],"features":["function-calling","reasoning","serverless"],"pricing":{"inputPerM":5500,"outputPerM":22000},"source":"public-provider-conf"},"vision":false},{"id":"minimax/minimax-m2.1","name":"Minimax M2.1","display_name":"Minimax M2.1","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"description":"MiniMax M2.1 is a cutting-edge AI model designed to revolutionize how developers build software. With enhanced multi-language programming support, it excels in generating high-quality code across popular languages like Rust, Java, Golang, C++, Kotlin, Objective-C, TypeScript, and JavaScript.\n\nKey improvements include:\n\n22% faster response times and 30% lower token consumption for efficient workflows.\nSeamless integration with leading development frameworks (Claude Code, Droid Factory AI, BlackBox, etc.).\nFull-stack development capabilities, from mobile (Android/iOS) to web and 3D interactive prototyping.\nOptimized performance-to-cost ratio, making AI-assisted development more accessible.\nWhether you're a software engineer, app developer, or tech innovator, M2.1 empowers smarter coding with industry-leading AI.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":3000,"outputPerM":12000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","display_name":"MiniMax M2.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"description":"MiniMax M2.1 is a cutting-edge AI model designed to revolutionize how developers build software. With enhanced multi-language programming support, it excels in generating high-quality code across popular languages like Rust, Java, Golang, C++, Kotlin, Objective-C, TypeScript, and JavaScript.\n\nKey improvements include:\n\n22% faster response times and 30% lower token consumption for efficient workflows.\nSeamless integration with leading development frameworks (Claude Code, Droid Factory AI, BlackBox, etc.).\nFull-stack development capabilities, from mobile (Android/iOS) to web and 3D interactive prototyping.\nOptimized performance-to-cost ratio, making AI-assisted development more accessible.\nWhether you're a software engineer, app developer, or tech innovator, M2.1 empowers smarter coding with industry-leading AI.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":3000,"outputPerM":12000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7-highspeed","display_name":"MiniMax M2.7-highspeed","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131072},"metadata":{"description":"MiniMax M2.7-highspeed is an accelerated SOTA model engineered for scenarios demanding extreme efficiency. It perfectly inherits the core intelligence and robust digital workspace capabilities of the standard M2.7.\nIn real-world software engineering, M2.7 excels by independently driving end-to-end project delivery while efficiently handling advanced tasks such as log analysis, bug troubleshooting, code security, and machine learning. In the professional workspace, it boasts the highest open-source GDPval-AA score (1495 ELO). It delivers high-fidelity, complex editing and multi-turn revisions across the Office suite (Excel, PPT, Word), elevating task execution to industry-leading standards.\nBuilt for complex environment interactions, M2.7 maintains an impressive 97% skill-following rate even with complex, long-context tool calls (>2000 tokens).  Beyond its robust productivity, M2.7 breaks the \"cold tool\" stereotype of traditional models. With exceptional identity retention and high emotional intelligence (EQ),","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":6000,"outputPerM":24000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5-highspeed","display_name":"MiniMax M2.5-highspeed","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":204800,"output":131100},"metadata":{"description":"MiniMax M2.5-highspeed is an accelerated SOTA model engineered for scenarios demanding extreme efficiency. It perfectly inherits the core intelligence and robust digital workspace capabilities of the standard M2.5—including its 80.2% score on SWE-Bench Verified, seamless manipulation of Office documents, and versatility in cross-software collaboration. With zero compromise on reasoning precision or logical depth, the Highspeed version delivers ultra-low latency inference through rigorous engineering optimization. This means you get more than just an intelligent assistant capable of planning and self-optimization; you gain a \"high-velocity engine\" that responds to high-frequency calls and processes complex document streams in near real-time, making it ideal for latency-sensitive interactive applications and large-scale automated pipelines.","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":6000,"outputPerM":24000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistralai/mistral-7b-instruct","name":"Mistral 7B Instruct","display_name":"Mistral 7B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32768,"output":8192},"metadata":{"description":"A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length.","endpoints":["chat/completions","completions"],"features":["serverless"],"pricing":{"inputPerM":290,"outputPerM":590},"source":"public-provider-conf"},"vision":false},{"id":"gryphe/mythomax-l2-13b","name":"Mythomax L2 13B","display_name":"Mythomax L2 13B","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":4096,"output":4096},"metadata":{"description":"The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time).","endpoints":["chat/completions","completions"],"features":["serverless"],"pricing":{"inputPerM":900,"outputPerM":900},"source":"public-provider-conf"},"vision":false},{"id":"nova-2-Lite","name":"nova-2-Lite","display_name":"nova-2-Lite","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":1000000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":3000,"outputPerM":25000},"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen 2.5 72B Instruct","display_name":"Qwen 2.5 72B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32000,"output":8192},"metadata":{"description":"Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters.","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":3800,"outputPerM":4000},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen-mt-plus","name":"Qwen MT Plus","display_name":"Qwen MT Plus","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":4096,"output":2048},"metadata":{"description":"Qwen-MT is a large language model optimized for machine translation, built upon the foundation of the Tongyi Qianwen model. It supports translation across 92 languages — including Chinese, English, Japanese, Korean, French, Spanish, German, Thai, Indonesian, Vietnamese, Arabic, and more — enabling seamless multilingual communication.","endpoints":["chat/completions"],"features":["serverless"],"pricing":{"inputPerM":2500,"outputPerM":7500},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen2.5-7b-instruct","name":"Qwen2.5 7B Instruct","display_name":"Qwen2.5 7B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":32000,"output":32000},"metadata":{"description":"Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":700,"outputPerM":700},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen2.5 VL 72B Instruct","display_name":"Qwen2.5 VL 72B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":32768,"output":32768},"metadata":{"description":"Qwen2.5-VL, the latest vision-language model in the Qwen2.5 series, delivers enhanced multimodal capabilities including advanced visual comprehension for object/text recognition, chart/layout analysis, and agent-based dynamic tool orchestration. It processes long-form videos (>1 hour) with key event detection while enabling precise spatial annotation through bounding boxes or coordinate points. The model specializes in structured data extraction from scanned documents (invoices, tables, etc.) and achieves state-of-the-art performance across multimodal benchmarks encompassing image understanding, temporal video analysis, and agent task evaluations.","endpoints":["chat/completions","completions"],"features":["serverless"],"pricing":{"inputPerM":8000,"outputPerM":8000},"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3B","display_name":"Qwen3 30B A3B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":40960,"output":20000},"metadata":{"description":"Achieves effective integration of inference and non-inference modes, allowing seamless switching between modes during conversations. Its inference capability matches that of QwQ-32B with a smaller parameter size, and its general capabilities significantly surpass those of Qwen2.5-14B, reaching the state-of-the-art (SOTA) level among models of the same scale.","endpoints":["chat/completions","completions"],"features":["reasoning","serverless"],"pricing":{"inputPerM":900,"outputPerM":4500},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-32b-fp8","name":"Qwen3 32B","display_name":"Qwen3 32B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":40960,"output":20000},"metadata":{"description":"Achieves effective integration of inference and non-inference modes, allowing seamless switching between modes during conversations. Its inference capability matches that of QwQ-32B with a smaller parameter size, and its general capabilities significantly surpass those of Qwen2.5-14B, reaching the state-of-the-art (SOTA) level among models of the same scale.","endpoints":["chat/completions","completions"],"features":["reasoning","serverless"],"pricing":{"inputPerM":1000,"outputPerM":4500},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B","display_name":"Qwen3 235B A22B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":40960,"output":20000},"metadata":{"description":"Achieves effective integration of inference and non-inference modes, enabling seamless switching between modes during conversations. The model's inference capability significantly surpasses that of QwQ, and its general capabilities exceed those of Qwen2.5-72B-Instruct, reaching the state-of-the-art (SOTA) level among models of the same scale.","endpoints":["chat/completions","completions"],"features":["reasoning","serverless"],"pricing":{"inputPerM":2000,"outputPerM":8000},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22b Thinking 2507","display_name":"Qwen3 235B A22b Thinking 2507","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":131072,"output":131072},"metadata":{"description":"The Qwen3-235B-A22B-Thinking-2507 represents the newest thinking-enabled model in the Qwen3 series, delivering groundbreaking improvements in reasoning capabilities. This advanced AI demonstrates significantly enhanced performance across logical reasoning, mathematics, scientific analysis, coding tasks, and academic benchmarks - matching or even surpassing human-expert level performance to achieve state-of-the-art results among open-source thinking models. Beyond its exceptional reasoning skills, the model shows markedly better general capabilities including more precise instruction following, sophisticated tool usage, highly natural text generation, and improved alignment with human preferences. It also features enhanced 256K long-context understanding, allowing it to maintain coherence and depth across extended documents and complex discussions.","endpoints":["chat/completions","completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":3000,"outputPerM":30000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","display_name":"Qwen3 Coder 480B A35B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"description":"Qwen3-Coder-480B-A35B-Instruct is a cutting-edge open coding model from Qwen, matching Claude Sonnet’s performance in agentic programming, browser automation, and core development tasks. With native 256K context (extendable to 1M tokens via YaRN), it excels at repository-scale analysis and features specialized function-call support for platforms like Qwen Code and CLINE—making it ideal for complex, real-world development workflows.","endpoints":["chat/completions","completions","anthropic"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":3800,"outputPerM":15500},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next FP8","display_name":"Qwen3 Coder Next FP8","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"description":"Qwen3-Coder-Next is an open-weight language model specifically engineered for coding agents and local development environments. This highly efficient model delivers exceptional performance with only 3B activated parameters out of 80B total parameters, achieving results comparable to models with 10-20x more active parameters while maintaining remarkable cost-effectiveness for agent deployment. Through its sophisticated training methodology, Qwen3-Coder-Next excels in advanced agentic capabilities including long-horizon reasoning, complex tool usage, and robust recovery from execution failures, ensuring reliable performance across dynamic coding tasks. The model's versatility is further enhanced by its 256k context length and adaptability to various scaffold templates, enabling seamless integration with diverse CLI/IDE platforms such as Claude Code, Qwen Code, Qoder, Kilo, Trae, and Cline, making it an ideal solution for comprehensive development environments.","endpoints":["chat/completions","completion","anthropic"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":2000,"outputPerM":15000},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","display_name":"Qwen3 Next 80B A3B Instruct","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":65536,"output":65536},"metadata":{"description":"Qwen3-Next uses a highly sparse MoE design: 80B total parameters, but only ~3B activated per inference step. Experiments show that, with global load balancing, increasing total expert parameters while keeping activated experts fixed steadily reduces training loss.Compared to Qwen3’s MoE (128 total experts, 8 routed), Qwen3-Next expands to 512 total experts, combining 10 routed experts + 1 shared expert — maximizing resource usage without hurting performance. The Qwen3-Next-80B-A3B-Instruct performs comparably to our flagship model Qwen3-235B-A22B-Instruct-2507, and shows clear advantages in tasks requiring ultra-long context (up to 256K tokens).","endpoints":["chat/completions","completions","anthropic"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":1500,"outputPerM":15000},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","display_name":"Qwen3 Next 80B A3B Thinking","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":65536,"output":65536},"metadata":{"description":"Qwen3-Next uses a highly sparse MoE design: 80B total parameters, but only ~3B activated per inference step. Experiments show that, with global load balancing, increasing total expert parameters while keeping activated experts fixed steadily reduces training loss.Compared to Qwen3’s MoE (128 total experts, 8 routed), Qwen3-Next expands to 512 total experts, combining 10 routed experts + 1 shared expert — maximizing resource usage without hurting performance. The Qwen3-Next-80B-A3B-Thinking excels at complex reasoning tasks — outperforming higher-cost models like Qwen3-30B-A3B-Thinking-2507 and Qwen3-32B-Thinking, outpeforming the closed-source Gemini-2.5-Flash-Thinking on multiple benchmarks, and approaching the performance of our top-tier model Qwen3-235B-A22B-Thinking-2507.","endpoints":["chat/completions","completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1500,"outputPerM":15000},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomimimo/mimo-v2-pro","name":"XiaomiMiMo/MiMo-V2-Pro","display_name":"XiaomiMiMo/MiMo-V2-Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"description":"Xiaomi’s MiMo-V2-Pro is a flagship, >1T parameter foundation model with a 1M context window, specifically optimized for advanced agentic workflows. Highly compatible with frameworks like OpenClaw, it secures top-tier global rankings on PinchBench and ClawBench, with a perceived capability approaching Opus 4.6. Built to act as the cognitive core of intelligent systems, MiMo-V2-Pro seamlessly orchestrates complex tasks, drives engineering automation, and consistently delivers dependable real-world outcomes.","endpoints":["completion","chat/completions","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3.5-27b","name":"Qwen3.5-27B","display_name":"Qwen3.5-27B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":65500},"metadata":{"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.","endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":3000,"outputPerM":24000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"gemini-nano-banana-2.1-as","name":"gemini-nano-banana-2.1-as","display_name":"gemini-nano-banana-2.1-as","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":15000,"outputPerM":75000},"source":"public-provider-conf"},"vision":true},{"id":"gemini-nano-banana-2.1","name":"gemini nano banana 2.1","display_name":"gemini nano banana 2.1","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":15000,"outputPerM":75000},"source":"public-provider-conf"},"vision":true},{"id":"claude-haiku-5-5","name":"claude-haiku-5-5","display_name":"claude-haiku-5-5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":1000,"outputPerM":5000},"source":"public-provider-conf"},"vision":true},{"id":"grok-4.7","name":"grok-4.7","display_name":"grok-4.7","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":500000},"metadata":{"endpoints":["chat/completions","responses"],"features":["serverless","function-calling","structured-outputs"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":true},{"id":"ming-image-0.1-design-layer","name":"ming image 0.1 design layer","display_name":"ming image 0.1 design layer","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":0,"outputPerM":0},"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-2.5-flare","name":"gpt image 2.5 flare","display_name":"gpt image 2.5 flare","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":50000,"outputPerM":300000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-2.5-sunburst","name":"gpt image 2.5 sunburst","display_name":"gpt image 2.5 sunburst","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":50000,"outputPerM":300000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-2.5-flare-oai","name":"gpt image 2.5 flare oai","display_name":"gpt image 2.5 flare oai","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":50000,"outputPerM":300000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-2.5-sunburst-oai","name":"gpt image 2.5 sunburst oai","display_name":"gpt image 2.5 sunburst oai","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":50000,"outputPerM":300000},"source":"public-provider-conf"},"vision":true},{"id":"grok-4.6","name":"grok-4.6","display_name":"grok-4.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":500000},"metadata":{"endpoints":["chat/completions","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"xai/grok-4.6","name":"xai/grok-4.6","display_name":"xai/grok-4.6","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":500000},"metadata":{"endpoints":["chat/completions","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","display_name":"Qwen3.8 Max","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":131702},"metadata":{"description":"A 2.4T-parameter MoE flagship for coding and knowledge work. Programs autonomously for days to deliver complete projects end to end, with native visual understanding across planning, execution, and verification, plus deep semantic analysis of ultra-long documents and video.","endpoints":["chat/completions","anthropic","responses"],"features":["serverless","reasoning","structured-outputs","function-calling"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-omni-flash","name":"gemini-omni-flash","display_name":"gemini-omni-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image","video","audio"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":15000,"outputPerM":90000},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.1-flash-lite-image-as","name":"gemini-3.1-flash-lite-image-as","display_name":"gemini-3.1-flash-lite-image-as","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image"]},"limit":{"context":65536,"output":65536},"metadata":{"features":["serverless"],"pricing":{"inputPerM":2500,"outputPerM":15000},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.1-flash-image-as","name":"gemini-3.1-flash-image-as","display_name":"gemini-3.1-flash-image-as","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image"]},"limit":{"context":65536,"output":65536},"metadata":{"features":["serverless"],"pricing":{"inputPerM":5000,"outputPerM":30000},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3-pro-image-as","name":"gemini-3-pro-image-as","display_name":"gemini-3-pro-image-as","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image"]},"limit":{"context":65536,"output":65536},"metadata":{"features":["serverless"],"pricing":{"inputPerM":20000,"outputPerM":120000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-image-as","name":"gemini-2.5-flash-image-as","display_name":"gemini-2.5-flash-image-as","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image"]},"limit":{"context":65536,"output":65536},"metadata":{"features":["serverless"],"pricing":{"inputPerM":3000,"outputPerM":300000},"source":"public-provider-conf"},"vision":true},{"id":"gemini-3.5-flash-lite","name":"gemini-3.5-flash-lite","display_name":"gemini-3.5-flash-lite","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"limit":{"context":1048576,"output":65536},"metadata":{"endpoints":["chat/completions","gemini","responses"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":3000,"outputPerM":25000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"grok-4.5","name":"grok-4.5","display_name":"grok-4.5","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":500000,"output":500000},"metadata":{"endpoints":["chat/completions"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-lite-image","name":"gemini-3.1-flash-lite-image","display_name":"gemini-3.1-flash-lite-image","type":"image-generation","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":2500,"outputPerM":15000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3.1-flash-image","name":"gemini-3.1-flash-image","display_name":"gemini-3.1-flash-image","type":"image-generation","reasoning":{"supported":true},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":5000,"outputPerM":30000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"gemini-3-pro-image","name":"gemini-3-pro-image","display_name":"gemini-3-pro-image","type":"image-generation","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":20000,"outputPerM":120000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"gemini-2.5-flash-image","name":"gemini-2.5-flash-image","display_name":"gemini-2.5-flash-image","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":3000,"outputPerM":300000},"source":"public-provider-conf"},"vision":true},{"id":"gpt-image-2","name":"gpt-image-2","display_name":"gpt-image-2","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["text","image"]},"limit":{"context":8192,"output":8192},"metadata":{"features":["serverless"],"pricing":{"inputPerM":50000,"outputPerM":300000},"source":"public-provider-conf"},"vision":true},{"id":"slow-mock","name":"slow-mock","display_name":"slow-mock","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":128000,"output":128000},"metadata":{"description":"timeout问题测试","endpoints":["chat/completions"],"features":["serverless"],"pricing":{"inputPerM":0,"outputPerM":0},"source":"public-provider-conf"},"vision":false},{"id":"claude-opus-4-8-cc","name":"claude-opus-4-8-cc","display_name":"claude-opus-4-8-cc","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":18500,"outputPerM":92500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-opus-4-6-cc","name":"claude-opus-4-6-cc","display_name":"claude-opus-4-6-cc","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":18500,"outputPerM":92500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-opus-4-7-cc","name":"claude-opus-4-7-cc","display_name":"claude-opus-4-7-cc","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"description":"Most intelligent model for building agents and coding","endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":18500,"outputPerM":92500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"claude-sonnet-4-6-cc","name":"claude-sonnet-4-6-cc","display_name":"claude-sonnet-4-6-cc","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":1000000,"output":128000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":11100,"outputPerM":55500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"claude-haiku-4-5-20251001-cc","name":"claude-haiku-4-5-20251001-cc","display_name":"claude-haiku-4-5-20251001-cc","type":"chat","reasoning":{"supported":true,"default":false},"tool_call":true,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":200000,"output":64000},"metadata":{"endpoints":["chat/completions","anthropic"],"features":["function-calling","structured-outputs","reasoning","serverless"],"pricing":{"inputPerM":3700,"outputPerM":18500},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"xiaomimimo/mimo-v2.5-pro","name":"XiaomiMiMo/MiMo-V2.5-Pro","display_name":"XiaomiMiMo/MiMo-V2.5-Pro","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":1048576,"output":131072},"metadata":{"description":"MiMo-V2.5-Pro is purpose-built to push the boundaries of complex software engineering and extreme long-horizon tasks. Compared to its predecessor, it achieves a comprehensive leap in general agentic capabilities, advancing the human-AI collaboration paradigm toward true \"autonomous delivery.\" Without human intervention, it stably orchestrates massive workflows requiring up to a thousand tool calls in a single session, not only precisely capturing implicit requirements within ultra-long contexts but also demonstrating exceptional global architectural planning and self-correction discipline. In core agentic scenarios and long-horizon complexities, MiMo-V2.5-Pro is fully equipped to go head-to-head with top-tier global models like Claude Opus 4.6 and GPT-5.4. Backed by this exceptionally high execution confidence and long-term logical consistency, it completely sheds the \"co-pilot\" label, ready to take on truly serious, professional-grade workloads in real-world business environments.","endpoints":["completion","chat/completions","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":20000,"outputPerM":60000},"source":"public-provider-conf"},"vision":false},{"id":"inclusionai/ring-2.6-1t","name":"Ring-2.6-1T","display_name":"Ring-2.6-1T","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":65536},"metadata":{"endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":3000,"outputPerM":25000},"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5-122B-A10B","display_name":"Qwen3.5-122B-A10B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":65500},"metadata":{"description":"The Qwen3.5-122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.","endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":4000,"outputPerM":32000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","display_name":"Qwen3.5-35B-A3B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":65500},"metadata":{"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.","endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":2500,"outputPerM":20000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","display_name":"Qwen3.5-397B-A17B","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":262144,"output":64000},"metadata":{"description":"The Qwen3.5 series 397B-A17B native vision-language model is based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency. Across a variety of tasks—including language understanding, logical reasoning, code generation, agentic tasks, image understanding, video understanding, and graphical user interface (GUI) interaction—it demonstrates exceptional performance comparable to current top-tier frontier models. Possessing robust code generation and agentic capabilities, it exhibits strong generalization across various agent scenarios.","endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":6000,"outputPerM":36000},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5-Plus","display_name":"Qwen3.5-Plus","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":1000000,"output":64000},"metadata":{"description":"The Qwen3.5 native vision-language series Plus models are based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency. Across various task evaluations, the 3.5 series demonstrates exceptional performance comparable to current top-tier frontier models, marking a leap forward in both plain text and multimodal capabilities compared to the 3 series.","endpoints":["chat/completions"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":0,"outputPerM":0},"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"xiaomimimo/mimo-v2-flash","name":"XiaomiMiMo/MiMo-V2-Flash","display_name":"XiaomiMiMo/MiMo-V2-Flash","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":262144,"output":131072},"metadata":{"endpoints":["chat/completions","completion","anthropic"],"features":["serverless","function-calling","structured-outputs","reasoning"],"pricing":{"inputPerM":1000,"outputPerM":3000},"source":"public-provider-conf"},"vision":false},{"id":"sao10k/l3-8b-lunaris","name":"Sao10k L3 8B Lunaris","display_name":"Sao10k L3 8B Lunaris","type":"chat","reasoning":{"supported":false},"tool_call":true,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"A generalist / roleplaying model merge based on Llama 3.","endpoints":["chat/completions","completions"],"features":["function-calling","structured-outputs","serverless"],"pricing":{"inputPerM":500,"outputPerM":500},"source":"public-provider-conf"},"vision":false}],"metadata":{"source":"public-provider-conf"}},"zenmux":{"id":"zenmux","name":"ZenMux","display_name":"ZenMux","updated_at":"2026-10-18T20:13:14.798Z","models":[{"id":"alibaba/wan3.0-video","name":"Alibaba: Wan3.0-Video","display_name":"Alibaba: Wan3.0-Video","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio","document","link"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wan 3.0 (Tongyi Wanxiang 3.0) is an integrated video generation and editing model launched by Alibaba’s Tongyi Lab. It is suitable for scenarios such as advertising, e-commerce, short films, character animation, video editing, and document-to-video. Its advantages include native support for videos up to 30 seconds long and the unified handling of reference content such as text, images, audio, video, documents, spreadsheets, presentations, and web pages, delivering more realistic visuals and audio, stable character consistency, and capabilities for referencing, editing, replication, and driving. Compared with Wan 2.7, which split text-to-video, image-to-video, reference generation, and editing across multiple models, Wan 3.0 integrates these capabilities into a single model, making the creative workflow more unified and flexible.","typeHints":["video"],"inputModalities":["text","image","video","audio","document","link"],"source":"public-provider-conf"},"vision":true},{"id":"alibaba/wan3.0-video-prime","name":"Alibaba: Wan3.0-Video-Prime","display_name":"Alibaba: Wan3.0-Video-Prime","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video","audio","document","link"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"Wan3.0 Video Prime is Alibaba Cloud’s preview high-speed edition of its All-in-One video model, positioned for faster-turnaround ads, ecommerce, short films, and editing. Aligned with Wan3.0 Video’s capabilities, it supports text-to-video, image-to-video, reference-based generation, document/webpage-to-video, up to 30 seconds at 30fps, 1080P output, adaptive aspect ratios, and native audio. It unifies modes that Wan 2.7 handled through separate task-specific models.","typeHints":["video"],"inputModalities":["text","image","video","audio","document","link"],"source":"public-provider-conf"},"vision":true},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","display_name":"Anthropic: Claude Fable 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":10,"output":50},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","display_name":"Anthropic: Claude Fable 5.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-06","release_date":"2026-09-01","last_updated":"2026-09-01","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Adaptive thinking is always on for Claude Fable 5 and Claude Mythos 5; thinking.type = \"disabled\" is rejected.","Manual budget_tokens requests return 400 on Claude Fable 5 and Claude Mythos 5.","thinking.display defaults to omitted; set display to summarized to receive readable thinking summaries."]}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","display_name":"Anthropic: Claude Haiku 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2025-10-15","last_updated":"2025-10-15","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":0.85,"output":4.3,"cache_read":0.085,"cache_write":1.1},"limit":{"context":192000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","display_name":"Anthropic: Claude Haiku 5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-06","release_date":"2026-10-07","last_updated":"2026-10-07","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","display_name":"Anthropic: Claude Opus 4.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":13,"output":64,"cache_read":1.3,"cache_write":16},"limit":{"context":196608,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","display_name":"Anthropic: Claude Opus 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2025-11-21","last_updated":"2025-11-21","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.3},"limit":{"context":196608,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude Opus 4.5 uses manual thinking.type = \"enabled\" with budget_tokens; effort can be used alongside the thinking budget.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header."]}}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","display_name":"Anthropic: Claude Opus 4.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2026-02-04","last_updated":"2026-02-04","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.3},"limit":{"context":983040,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","display_name":"Anthropic: Claude Opus 4.7","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2026-04-15","last_updated":"2026-04-15","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.4},"limit":{"context":1048576,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","display_name":"Anthropic: Claude Opus 4.8","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4.2929,"output":21.4646},"limit":{"context":1048576,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"high","effort_options":["low","medium","high","xhigh","max"],"interleaved":true,"summaries":true,"visibility":"omitted","continuation":["thinking_blocks"],"notes":["Claude Opus 4.7 and newer Opus models require thinking.type = \"adaptive\" to enable thinking explicitly.","Manual budget_tokens requests return 400 on Claude Opus 4.7 and newer adaptive-only Opus models.","task_budget is separate from thinking control and should not be treated as a thinking budget."]}}},{"id":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","display_name":"Anthropic: Claude Opus 5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","display_name":"Anthropic: Claude Opus 5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-06","release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":4,"output":20,"cache_read":0.2,"cache_write":5},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","display_name":"Anthropic: Claude Sonnet 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2025-09-26","last_updated":"2025-09-26","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"limit":{"context":983040,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":1024,"unit":"tokens"},"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Claude 4 manual thinking uses thinking.type = \"enabled\" with budget_tokens.","Interleaved thinking requires the interleaved-thinking-2025-05-14 beta header for this model family."]}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","display_name":"Anthropic: Claude Sonnet 4.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2026-02-05","last_updated":"2026-02-05","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"limit":{"context":983040,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"mixed","budget":{"min":1024,"unit":"tokens"},"effort":"high","effort_options":["low","medium","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["Anthropic recommends adaptive thinking with effort for Claude 4.6; budget_tokens remains a deprecated compatibility path.","Anthropic API defaults effort to high; lower effort levels should be chosen per workload."]}}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","display_name":"Anthropic: Claude Sonnet 5","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":false,"tool_call":true,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","display_name":"Anthropic: Claude Sonnet 5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-06","release_date":"2026-09-28","last_updated":"2026-09-28","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"atria-asi/atria-dawn","name":"Atria: Atria Dawn (Free)","display_name":"Atria: Atria Dawn (Free)","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"limit":{"context":524288,"output":65536},"metadata":{"ownedBy":"atria-asi","created":1792132430,"source":"public-provider-conf"},"vision":false},{"id":"atria-asi/atria-dawn-preview","name":"Atria: Atria Dawn Preview (Free)","display_name":"Atria: Atria Dawn Preview (Free)","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"limit":{"context":262144,"output":65536},"metadata":{"ownedBy":"atria-asi","created":1789364855,"source":"public-provider-conf"},"vision":false},{"id":"baidu/ernie-5.0-thinking-preview","name":"Baidu: ERNIE 5.0","display_name":"Baidu: ERNIE 5.0","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01-01","release_date":"2026-01-22","last_updated":"2026-01-22","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.84,"output":3.37},"limit":{"context":128000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"baidu/ernie-5.1","name":"Baidu: ERNIE 5.1","display_name":"Baidu: ERNIE 5.1","type":"chat","attachment":false,"reasoning":{"supported":true},"tool_call":false,"release_date":"2026-05-10","last_updated":"2026-05-10","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.75,"output":3,"cache_read":0.75},"limit":{"context":119000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"baidu/ernie-x1.1-preview","name":"Baidu: ERNIE-X1.1-Preview","display_name":"Baidu: ERNIE-X1.1-Preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":true,"modalities":{"input":["text"]},"cost":{"input":0.136,"output":0.544},"limit":{"context":119000,"output":119000},"metadata":{"description":"The Wenxin large model X1.1 has made significant improvements in question answering, tool invocation, intelligent agents, instruction following, logical reasoning, mathematics, and coding tasks, with notable enhancements in factual accuracy. The context length has been extended to 64K tokens, supporting longer inputs and dialogue history, which improves the coherence of long-chain reasoning while maintaining response speed.","typeHints":["llm"],"features":["thinking","tools","function_calling","structured_outputs"],"inputModalities":["text"],"pricing":{"input":0.136,"output":0.544},"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"bfl/flux-3-video","name":"Black Forest Labs: FLUX.3 Video","display_name":"Black Forest Labs: FLUX.3 Video","type":"image-generation","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-04","last_updated":"2026-08-04","open_weights":false,"modalities":{"input":["text"],"output":["video"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"bytedance/doubao-seed-1.8","name":"ByteDance: Doubao-Seed-1.8","display_name":"ByteDance: Doubao-Seed-1.8","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01-01","release_date":"2025-12-18","last_updated":"2025-12-18","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.11,"output":0.28,"cache_read":0.02,"cache_write":0.0024},"limit":{"context":256000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seed-2.0-code","name":"ByteDance: Doubao-Seed-2.0-Code","display_name":"ByteDance: Doubao-Seed-2.0-Code","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-02-14","last_updated":"2026-02-14","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":256000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seed-2.0-lite","name":"ByteDance: Doubao-Seed-2.0-lite","display_name":"ByteDance: Doubao-Seed-2.0-lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-02-14","last_updated":"2026-02-14","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":256000,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seed-2.0-mini","name":"ByteDance: Doubao-Seed-2.0-mini","display_name":"ByteDance: Doubao-Seed-2.0-mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-02-14","last_updated":"2026-02-14","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":256000,"output":32000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seed-2.0-pro","name":"ByteDance: Doubao-Seed-2.0-pro","display_name":"ByteDance: Doubao-Seed-2.0-pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-02-14","last_updated":"2026-02-14","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"limit":{"context":256000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seed-2.1-pro","name":"ByteDance: Doubao-Seed-2.1-pro","display_name":"ByteDance: Doubao-Seed-2.1-pro","type":"chat","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-06-23","last_updated":"2026-06-23","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":1,"output":5,"cache_read":0.5},"limit":{"context":256000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"bytedance/doubao-seed-2.1-turbo","name":"ByteDance: Doubao-Seed-2.1-turbo","display_name":"ByteDance: Doubao-Seed-2.1-turbo","type":"chat","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-06-23","last_updated":"2026-06-23","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"limit":{"context":256000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"bytedance/doubao-seed-asr-2.0","name":"ByteDance: Doubao-Seed-ASR-2.0","display_name":"ByteDance: Doubao-Seed-ASR-2.0","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"],"output":["transcription"]},"limit":{"context":1024,"output":1024},"metadata":{"ownedBy":"bytedance","created":1782724491,"source":"public-provider-conf"},"vision":false},{"id":"bytedance/doubao-seed-character","name":"ByteDance: Doubao-Seed-Character","display_name":"ByteDance: Doubao-Seed-Character","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":false,"release_date":"2026-07-18","last_updated":"2026-07-18","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.15,"output":0.37,"cache_read":0.03,"cache_write":0.003},"limit":{"context":128000,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seed-code","name":"ByteDance: Doubao-Seed-Code","display_name":"ByteDance: Doubao-Seed-Code","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01-01","release_date":"2025-11-11","last_updated":"2025-11-11","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.17,"output":1.12,"cache_read":0.03},"limit":{"context":256000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seed-evolving","name":"ByteDance: Doubao-Seed-Evolving","display_name":"ByteDance: Doubao-Seed-Evolving","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-06-23","last_updated":"2026-06-23","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.8906,"output":4.45301,"cache_read":0.17812},"limit":{"context":256000,"output":256000},"metadata":{"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"bytedance/doubao-seedance-2.0","name":"ByteDance: Doubao-Seedance-2.0","display_name":"ByteDance: Doubao-Seedance-2.0","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","audio","video"],"output":["video"]},"limit":{"context":12800,"output":12800},"metadata":{"ownedBy":"bytedance","created":1775530721,"source":"public-provider-conf"},"vision":true},{"id":"bytedance/doubao-seedance-2.5","name":"ByteDance: Doubao-Seedance-2.5","display_name":"ByteDance: Doubao-Seedance-2.5","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","audio","video"],"output":["video"]},"limit":{"context":12800,"output":12800},"metadata":{"ownedBy":"bytedance","created":1786096108,"source":"public-provider-conf"},"vision":true},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","display_name":"DeepSeek: DeepSeek V3.2","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":true,"tool_call":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","open_weights":true,"modalities":{"input":["text","pdf"],"output":["text"]},"cost":{"input":0.2088,"output":0.3096,"cache_read":0.0216},"limit":{"context":163000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0731","display_name":"DeepSeek: DeepSeek V4 Flash 0731","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"limit":{"context":1048576,"output":384000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0813","display_name":"DeepSeek: DeepSeek V4 Pro 0813","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.7,"output":1.4,"cache_read":0.07},"limit":{"context":1048576,"output":384000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["low","high","max"],"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"],"notes":["The DeepSeek API maps medium and xhigh to high for V4 models; effort_options lists distinct model-effective levels."]}}},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","display_name":"DeepSeek: DeepSeek V4.1 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-05","release_date":"2026-09-10","last_updated":"2026-09-10","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.09,"output":0.3,"cache_read":0.006},"limit":{"context":1000000,"output":384000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"dots-studio/dots3-note-prev","name":"Dots Studio: Dots3-Note Preview (Free)","display_name":"Dots Studio: Dots3-Note Preview (Free)","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":0,"output":0,"cache_read":0},"limit":{"context":393100,"output":393100},"metadata":{"ownedBy":"dots-studio","created":1786962877,"source":"public-provider-conf"},"vision":true},{"id":"google/gemini-3.1-flash-tts-preview","name":"Gemini 3.1 Flash TTS Preview","display_name":"Gemini 3.1 Flash TTS Preview","type":"audio","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":false,"knowledge":"2025-01","release_date":"2026-04-15","last_updated":"2026-04-15","open_weights":false,"modalities":{"input":["text"],"output":["audio"]},"cost":{"input":1,"output":20},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"google/gemini-3.8-flash-lite-tts","name":"Gemini 3.8 Flash Lite TTS","display_name":"Gemini 3.8 Flash Lite TTS","type":"audio","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-23","last_updated":"2026-09-23","open_weights":false,"modalities":{"input":["text"],"output":["audio"]},"cost":{"input":0.5,"output":6},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"google/gemini-3.8-flash-tts","name":"Gemini 3.8 Flash TTS","display_name":"Gemini 3.8 Flash TTS","type":"audio","attachment":false,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-09-23","last_updated":"2026-09-23","open_weights":false,"modalities":{"input":["text"],"output":["audio"]},"cost":{"input":0.5,"output":9},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","display_name":"Google: Gemini 2.5 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","open_weights":false,"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":0,"max":24576,"default":-1,"auto":-1,"off":0,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","display_name":"Google: Gemini 2.5 Flash Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2025-06-19","last_updated":"2025-06-19","open_weights":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":0.07,"output":0.28},"limit":{"context":1024000,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"budget","budget":{"min":512,"max":24576,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","display_name":"Google: Gemini 2.5 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","open_weights":false,"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"budget","budget":{"min":128,"max":32768,"default":-1,"auto":-1,"unit":"tokens"},"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","display_name":"Google: Gemini 3 Flash Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":0.5,"output":3,"cache_read":0.05},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","display_name":"Google: Gemini 3.1 Flash Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","open_weights":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":0.2525,"output":1.5152},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","display_name":"Google: Gemini 3.1 Pro Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":2,"output":12,"cache_read":0.2},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["low","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","display_name":"Google: Gemini 3.5 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":1.5152,"output":9.0909,"cache_read":0.1515},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","display_name":"Google: Gemini 3.5 Flash Lite","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","open_weights":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":0.303,"output":2.5253,"cache_read":0.0303},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"google/gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","display_name":"Google: Gemini 3.6 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","open_weights":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":0.7576,"output":3.7879,"cache_read":0.0758},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","display_name":"Google: Gemini 3.7 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","open_weights":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":0.7576,"output":3.7879,"cache_read":0.0758},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","display_name":"Google: Gemini 3.8 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-02","last_updated":"2026-09-02","open_weights":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":0.7576,"output":3.7879,"cache_read":0.0758},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"level","level":"high","level_options":["minimal","low","medium","high"],"summaries":true,"visibility":"summary","continuation":["thought_signatures"]}}},{"id":"google/gemini-4-argon","name":"Google: Gemini 4 Argon","display_name":"Google: Gemini 4 Argon","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-03","release_date":"2026-10-13","last_updated":"2026-10-13","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":0.1875},"limit":{"context":1048576,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"google/gemini-embedding-2","name":"Google: Gemini Embedding 2","display_name":"Google: Gemini Embedding 2","type":"embedding","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B IT","display_name":"Google: Gemma 4 26B A4B IT","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-04-02","last_updated":"2026-04-02","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.07,"output":0.34},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B IT","display_name":"Google: Gemma 4 31B IT","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-04-02","last_updated":"2026-04-02","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.2,"output":0.4},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"x-ai/grok-imagine-image-2.0","name":"Grok Imagine Image 2.0","display_name":"Grok Imagine Image 2.0","type":"image-generation","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-08-07","last_updated":"2026-08-07","open_weights":false,"modalities":{"input":["text","image"],"output":["image"]},"limit":{"context":66000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"inclusionai/ling-2.6-1t","name":"inclusionAI: Ling-2.6-1T","display_name":"inclusionAI: Ling-2.6-1T","type":"chat","attachment":false,"reasoning":{"supported":false},"tool_call":true,"release_date":"2026-04-23","last_updated":"2026-04-23","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.3,"output":2.5},"limit":{"context":262144,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"inclusionai/ling-2.6-flash","name":"inclusionAI: Ling-2.6-flash","display_name":"inclusionAI: Ling-2.6-flash","type":"chat","attachment":false,"reasoning":{"supported":false},"tool_call":true,"release_date":"2026-04-21","last_updated":"2026-04-21","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.1,"output":0.3},"limit":{"context":262144,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"inclusionai/ling-3.0-flash","name":"inclusionAI: Ling-3.0-flash","display_name":"inclusionAI: Ling-3.0-flash","type":"chat","attachment":false,"reasoning":{"supported":true},"temperature":true,"tool_call":true,"release_date":"2026-07-23","last_updated":"2026-07-23","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionai/ling-3.0-flash-fin","name":"inclusionAI: Ling-3.0-flash-Fin","display_name":"inclusionAI: Ling-3.0-flash-Fin","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"release_date":"2026-08-27","last_updated":"2026-09-03","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"inclusionai/ling-3.0-flash-sante","name":"inclusionAI: Ling-3.0-flash-Sante","display_name":"inclusionAI: Ling-3.0-flash-Sante","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-04","last_updated":"2026-09-04","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"inclusionai/ling-3.0-flash-vl","name":"inclusionAI: Ling-3.0-flash-VL","display_name":"inclusionAI: Ling-3.0-flash-VL","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-10","last_updated":"2026-09-10","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"inclusionai/ling-3.0-tiny","name":"inclusionAI: Ling-3.0-tiny","display_name":"inclusionAI: Ling-3.0-tiny","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"release_date":"2026-08-05","last_updated":"2026-08-05","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0,"output":0},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"inclusionai/ling-3.1-flash","name":"inclusionAI: Ling-3.1-flash","display_name":"inclusionAI: Ling-3.1-flash","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"tool_call":true,"release_date":"2026-09-29","last_updated":"2026-09-29","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"inclusionai/llada-image","name":"inclusionAI: LLaDA-Image","display_name":"inclusionAI: LLaDA-Image","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["image"]},"limit":{"context":2000,"output":2000},"metadata":{"ownedBy":"inclusionai","created":1791861343,"source":"public-provider-conf"},"vision":true},{"id":"inclusionai/llada-image-turbo","name":"inclusionAI: LLaDA-Image-Turbo","display_name":"inclusionAI: LLaDA-Image-Turbo","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["image"]},"limit":{"context":2000,"output":2000},"metadata":{"ownedBy":"inclusionai","created":1789648400,"source":"public-provider-conf"},"vision":true},{"id":"inclusionai/llada2.1-flash","name":"inclusionAI: LLaDA2.1-flash","display_name":"inclusionAI: LLaDA2.1-flash","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.28,"output":2.85,"cache_read":0.057},"limit":{"context":32000,"output":32000},"metadata":{"ownedBy":"inclusionai","created":1773648925,"source":"public-provider-conf"},"vision":false},{"id":"inclusionai/ming-image-0.1-design","name":"inclusionAI: Ming Image 0.1 Design","display_name":"inclusionAI: Ming Image 0.1 Design","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"],"output":["image"]},"cost":{"input":0,"output":0},"limit":{"context":8000,"output":8000},"metadata":{"ownedBy":"inclusionai","created":1790148935,"source":"public-provider-conf"},"vision":true},{"id":"inclusionai/ming-image-0.1-design-layer","name":"inclusionAI: Ming Image 0.1 Design Layer","display_name":"inclusionAI: Ming Image 0.1 Design Layer","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["image"]},"cost":{"input":0,"output":0},"limit":{"context":8000,"output":8000},"metadata":{"ownedBy":"inclusionai","created":1790215997,"source":"public-provider-conf"},"vision":true},{"id":"inclusionai/ring-2.6-1t","name":"inclusionAI: Ring-2.6-1T","display_name":"inclusionAI: Ring-2.6-1T","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-12-31","release_date":"2026-05-07","last_updated":"2026-05-14","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"limit":{"context":262000,"output":65000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"klingai/kling-3.0","name":"KlingAI: Kling-3.0","display_name":"KlingAI: Kling-3.0","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["video"]},"limit":{"context":20000,"output":20000},"metadata":{"ownedBy":"klingai","created":1788259485,"source":"public-provider-conf"},"vision":true},{"id":"klingai/kling-3.0-omni","name":"KlingAI: Kling-3.0-Omni","display_name":"KlingAI: Kling-3.0-Omni","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"],"output":["video"]},"limit":{"context":20000,"output":20000},"metadata":{"ownedBy":"klingai","created":1788337250,"source":"public-provider-conf"},"vision":true},{"id":"klingai/kling-3.0-turbo","name":"KlingAI: Kling-3.0-Turbo","display_name":"KlingAI: Kling-3.0-Turbo","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["video"]},"limit":{"context":20000,"output":20000},"metadata":{"ownedBy":"klingai","created":1788259643,"source":"public-provider-conf"},"vision":true},{"id":"meituan/longcat-2.0","name":"Meituan: LongCat-2.0","display_name":"Meituan: LongCat-2.0","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07-20","last_updated":"2026-07-20","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.75,"output":3,"cache_read":0.015},"limit":{"context":1048756,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meituan/longcat-2.5-preview","name":"Meituan: LongCat-2.5-Preview","display_name":"Meituan: LongCat-2.5-Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"release_date":"2026-09-26","last_updated":"2026-09-26","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"meta/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","display_name":"Meta: Llama 3.3 70B Instruct","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.22,"output":0.5,"cache_read":0.11},"limit":{"context":131072,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"meta/llama-4-scout-17b-16e-instruct","name":"Meta: Llama 4 Scout Instruct","display_name":"Meta: Llama 4 Scout Instruct","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.2,"output":0.78},"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"meta/muse-image-1.0","name":"Meta: Muse Image 1.0","display_name":"Meta: Muse Image 1.0","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-26","last_updated":"2026-08-26","open_weights":false,"modalities":{"input":["text","image"],"output":["image"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"meta/muse-spark-1.1","name":"Meta: Muse Spark 1.1","display_name":"Meta: Muse Spark 1.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":false,"release_date":"2026-04-08","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","video","audio"],"output":["text"]},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.2","name":"Meta: Muse Spark 1.2","display_name":"Meta: Muse Spark 1.2","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-08-05","last_updated":"2026-08-05","open_weights":false,"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.3","name":"Meta: Muse Spark 1.3","display_name":"Meta: Muse Spark 1.3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-02","last_updated":"2026-09-02","open_weights":false,"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"meta/muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","display_name":"Meta: Muse Spark 1.3 Contributor","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"release_date":"2026-09-02","last_updated":"2026-09-02","open_weights":false,"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"limit":{"context":1048576,"output":943718},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"meta/muse-wonder-1.0","name":"Meta: Muse Wonder","display_name":"Meta: Muse Wonder","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-10-12","last_updated":"2026-10-12","open_weights":false,"modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"cost":{"input":4,"output":20,"cache_read":0.2},"limit":{"context":1048576,"output":1048576},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mindai/macaron-v1-tall","name":"Mind Lab: Macaron V1 Tall","display_name":"Mind Lab: Macaron V1 Tall","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07-21","last_updated":"2026-07-21","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.2475,"output":1.43,"cache_read":0.044},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"mindai/macaron-v1-venti","name":"Mind Lab: Macaron V1 Venti","display_name":"Mind Lab: Macaron V1 Venti","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07-21","last_updated":"2026-07-21","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.825,"output":2.475,"cache_read":0.165},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-h3","name":"MiniMax: MiniMax H3","display_name":"MiniMax: MiniMax H3","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-07-31","last_updated":"2026-10-04","open_weights":true,"modalities":{"input":["text","image"],"output":["video"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"minimax/minimax-h3-fast","name":"MiniMax: MiniMax H3 Fast","display_name":"MiniMax: MiniMax H3 Fast","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","audio","video"],"output":["video"]},"limit":{"context":12800,"output":12800},"metadata":{"ownedBy":"minimax","created":1792061858,"source":"public-provider-conf"},"vision":true},{"id":"minimax/minimax-h3-max","name":"MiniMax: MiniMax H3 Max","display_name":"MiniMax: MiniMax H3 Max","type":"image-generation","attachment":true,"reasoning":{"supported":false},"tool_call":false,"release_date":"2026-08-27","last_updated":"2026-08-27","open_weights":false,"modalities":{"input":["text","image"],"output":["video"]},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","display_name":"MiniMax: MiniMax M2","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":false,"release_date":"2025-10-27","last_updated":"2025-10-27","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.17,"output":1.53,"cache_read":0.085},"limit":{"context":200000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"minimax/minimax-m2-her","name":"MiniMax: MiniMax M2-her","display_name":"MiniMax: MiniMax M2-her","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"release_date":"2026-01-23","last_updated":"2026-01-23","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.302,"output":1.207,"cache_read":0.151},"limit":{"context":65532,"output":2048},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","display_name":"MiniMax: MiniMax M2.1","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2025-12-23","last_updated":"2025-12-23","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.33,"output":1.32,"cache_read":0.03},"limit":{"context":200000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","display_name":"MiniMax: MiniMax M2.5","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-02-12","last_updated":"2026-02-12","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.27,"output":1.08,"cache_read":0.027},"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"minimax/minimax-m2.5-lightning","name":"MiniMax: MiniMax M2.5 highspeed","display_name":"MiniMax: MiniMax M2.5 highspeed","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01-01","release_date":"2026-02-13","last_updated":"2026-02-13","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.6,"output":4.8,"cache_read":0.06,"cache_write":0.75},"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","display_name":"MiniMax: MiniMax M2.7","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-03-18","last_updated":"2026-03-18","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.21,"output":0.84,"cache_read":0.042},"limit":{"context":204800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax: MiniMax M2.7 highspeed","display_name":"MiniMax: MiniMax M2.7 highspeed","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-03-18","last_updated":"2026-03-18","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.6,"output":2.4,"cache_read":0.06},"limit":{"context":204800,"output":131100},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","display_name":"MiniMax: MiniMax M3","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":true,"tool_call":true,"release_date":"2026-06-01","last_updated":"2026-06-01","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.23,"output":0.96,"cache_read":0.05},"limit":{"context":512000,"output":80000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"mistralai/mistral-large-2512","name":"Mistral: Mistral Large 3","display_name":"Mistral: Mistral Large 3","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"knowledge":"2024-11","release_date":"2025-12-02","last_updated":"2025-12-02","open_weights":true,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"limit":{"context":262144,"output":209715},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"mistralai/mistral-large-4","name":"Mistral: Mistral Large 4","display_name":"Mistral: Mistral Large 4","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-10-06","last_updated":"2026-10-06","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.68,"output":2.09,"cache_read":0.07},"limit":{"context":524288,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","display_name":"MoonshotAI: Kimi K2.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2024-04","release_date":"2026-04-21","last_updated":"2026-04-21","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.75,"output":3.5,"cache_read":0.15},"limit":{"context":262144,"output":16384},"metadata":{"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","display_name":"MoonshotAI: Kimi K2.7 Code","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.68,"output":3.4,"cache_read":0.136},"limit":{"context":262144,"output":262144},"metadata":{"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"MoonshotAI: Kimi K2.7 Code HighSpeed","display_name":"MoonshotAI: Kimi K2.7 Code HighSpeed","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.9,"output":8,"cache_read":0.32},"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"moonshotai/kimi-k2.8-preview","name":"MoonshotAI: Kimi K2.8 Preview","display_name":"MoonshotAI: Kimi K2.8 Preview","type":"chat","reasoning":{"supported":true,"default":true},"tool_call":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":1,"output":4,"cache_read":0.25},"limit":{"context":1048576,"output":1048576},"metadata":{"ownedBy":"moonshotai","created":1789379421,"source":"public-provider-conf"},"vision":true},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","display_name":"MoonshotAI: Kimi K3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2026-07-16","last_updated":"2026-07-16","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2.85,"output":14.25,"cache_read":0.285},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/chat-latest","name":"OpenAI: Chat Latest (GPT-5.5 Instant)","display_name":"OpenAI: Chat Latest (GPT-5.5 Instant)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-12-01","release_date":"2026-05-05","last_updated":"2026-05-28","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":5,"output":30,"cache_read":0.5},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-transcribe","name":"OpenAI: GPT Transcribe","display_name":"OpenAI: GPT Transcribe","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"],"output":["transcription"]},"limit":{"context":15000,"output":15000},"metadata":{"ownedBy":"openai","created":1786436995,"source":"public-provider-conf"},"vision":false},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","display_name":"OpenAI: GPT-4.1","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"release_date":"2025-04-14","last_updated":"2025-04-14","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.8,"output":7.2,"cache_read":0.45},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","display_name":"OpenAI: GPT-4.1 Mini","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"release_date":"2025-04-15","last_updated":"2025-04-15","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.36,"output":1.4,"cache_read":0.09},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","display_name":"OpenAI: GPT-4.1 Nano","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"release_date":"2025-04-15","last_updated":"2025-04-15","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.09,"output":0.36,"cache_read":0.022},"limit":{"context":1047576,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o","name":"OpenAI: GPT-4o","display_name":"OpenAI: GPT-4o","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"release_date":"2024-05-13","last_updated":"2024-05-13","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","display_name":"OpenAI: GPT-4o-mini","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":true,"release_date":"2024-07-18","last_updated":"2024-07-18","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.14,"output":0.54,"cache_read":0.068},"limit":{"context":124096,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","display_name":"OpenAI: GPT-5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.1,"output":9,"cache_read":0.11},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-codex","name":"OpenAI: GPT-5 Codex","display_name":"OpenAI: GPT-5 Codex","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-09-23","last_updated":"2025-09-23","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.1,"output":9},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","display_name":"OpenAI: GPT-5 Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.25,"output":2,"cache_read":0.025},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","display_name":"OpenAI: GPT-5 Nano","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.045,"output":0.36,"cache_read":0.0045},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["minimal","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","display_name":"OpenAI: GPT-5 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-10-06","last_updated":"2025-10-06","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":14,"output":110},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"fixed","effort":"high","verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","display_name":"OpenAI: GPT-5.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.25,"output":10,"cache_read":0.125},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","display_name":"OpenAI: GPT-5.1-Codex","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2025-11-12","last_updated":"2025-11-12","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.1,"output":9,"cache_read":0.11},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","display_name":"OpenAI: GPT-5.1-Codex-Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2025-11-12","last_updated":"2025-11-12","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.22,"output":1.8,"cache_read":0.022},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","display_name":"OpenAI: GPT-5.2","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.75,"output":14,"cache_read":0.175},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","display_name":"OpenAI: GPT-5.2 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-12-11","last_updated":"2025-12-11","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":19,"output":150},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","display_name":"OpenAI: GPT-5.2-Codex","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2026-01-14","last_updated":"2026-01-14","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.6,"output":13,"cache_read":0.16},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","display_name":"OpenAI: GPT-5.3-Codex","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2026-02-10","last_updated":"2026-02-10","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.6,"output":13,"cache_read":0.16},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","display_name":"OpenAI: GPT-5.4","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2.5,"output":15,"cache_read":0.25},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","display_name":"OpenAI: GPT-5.4 Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2026-03-12","last_updated":"2026-03-12","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.68,"output":4,"cache_read":0.068},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","display_name":"OpenAI: GPT-5.4 Nano","type":"chat","attachment":true,"reasoning":{"supported":true,"default":false},"temperature":false,"tool_call":true,"release_date":"2026-03-11","last_updated":"2026-03-11","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.18,"output":1.1,"cache_read":0.018},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":false,"mode":"effort","effort":"none","effort_options":["none","low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","display_name":"OpenAI: GPT-5.4 Pro","type":"image-generation","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2026-03-05","last_updated":"2026-03-05","open_weights":false,"modalities":{"input":["text","image"],"output":["image"]},"cost":{"input":27,"output":160},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"high","effort_options":["medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","display_name":"OpenAI: GPT-5.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":5,"output":30,"cache_read":0.5},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high","xhigh"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","display_name":"OpenAI: GPT-5.5 Pro","type":"image-generation","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2025-12-01","release_date":"2026-04-08","last_updated":"2026-04-08","open_weights":false,"modalities":{"input":["text","image"],"output":["text","image"]},"cost":{"input":27.2727,"output":163.6364},"limit":{"context":400000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","display_name":"OpenAI: GPT-5.6 Luna","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","display_name":"OpenAI: GPT-5.6 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","display_name":"OpenAI: GPT-5.6 Terra","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["none","low","medium","high","xhigh","max"],"verbosity":"medium","verbosity_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","display_name":"OpenAI: GPT-6 Astra","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-04-30","release_date":"2026-09-04","last_updated":"2026-09-04","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","display_name":"OpenAI: GPT-6 Luna","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-05-18","release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","display_name":"OpenAI: GPT-6 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-04-20","release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","display_name":"OpenAI: GPT-6.1 Sol","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-04-30","release_date":"2026-09-29","last_updated":"2026-09-29","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5},"limit":{"context":1050000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-image-1.5","name":"OpenAI: GPT-Image-1.5","display_name":"OpenAI: GPT-Image-1.5","type":"image-generation","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2025-12-16","last_updated":"2025-12-16","open_weights":false,"modalities":{"input":["text","image"],"output":["image"]},"limit":{"context":128000,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-image-2","name":"OpenAI: GPT-Image-2","display_name":"OpenAI: GPT-Image-2","type":"image-generation","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-04-21","last_updated":"2026-04-21","open_weights":false,"modalities":{"input":["text","image"],"output":["image"]},"cost":{"input":5.0505,"output":32.3232,"cache_read":1.2626},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-image-2.5-flare","name":"OpenAI: GPT-Image-2.5-Flare","display_name":"OpenAI: GPT-Image-2.5-Flare","type":"image-generation","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-09-08","last_updated":"2026-09-08","open_weights":false,"modalities":{"input":["text"],"output":["image"]},"cost":{"input":5,"output":30,"cache_read":1.25},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/gpt-image-2.5-sunburst","name":"OpenAI: GPT-Image-2.5-Sunburst","display_name":"OpenAI: GPT-Image-2.5-Sunburst","type":"image-generation","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-09-08","last_updated":"2026-09-08","open_weights":false,"modalities":{"input":["text"],"output":["image"]},"cost":{"input":5,"output":30,"cache_read":1.25},"limit":{"context":8192,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","display_name":"OpenAI: o4 Mini","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"release_date":"2025-04-16","last_updated":"2025-04-16","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.99,"output":4,"cache_read":0.25},"limit":{"context":200000,"output":100000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"default_enabled":true,"mode":"effort","effort":"medium","effort_options":["low","medium","high"],"visibility":"hidden"}}},{"id":"openai/text-embedding-3-large","name":"OpenAI: Text Embedding 3 Large","display_name":"OpenAI: Text Embedding 3 Large","type":"embedding","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":1536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"openai/text-embedding-3-small","name":"OpenAI: Text Embedding 3 Small","display_name":"OpenAI: Text Embedding 3 Small","type":"embedding","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"limit":{"context":8192,"output":1536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"pixverse/c1","name":"PixVerse: C1","display_name":"PixVerse: C1","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image"],"output":["video"]},"limit":{"context":8192,"output":8192},"metadata":{"ownedBy":"pixverse","created":1786361333,"source":"public-provider-conf"},"vision":true},{"id":"pixverse/v6","name":"PixVerse: V6","display_name":"PixVerse: V6","type":"image-generation","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"],"output":["video"]},"limit":{"context":8192,"output":8192},"metadata":{"ownedBy":"pixverse","created":1786436837,"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen-audio-3.0-tts-plus","name":"Qwen-Audio-3.0-TTS-Plus","display_name":"Qwen-Audio-3.0-TTS-Plus","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text"]},"limit":{"context":8192,"output":8192},"metadata":{"description":"qwen-audio-3.0-tts-plus is a high-performance speech synthesis large model designed for high-quality speech generation scenarios. Compared with the previous version, the model supports more low-resource languages and Chinese dialects, significantly improving the authenticity of dialect pronunciation, and enhancing free-style instruction following and fine-grained label control capabilities, allowing more accurate control of emotion, tone, character, speaking rate, volume, and synthesis style. Meanwhile, the model exhibits stronger robustness under complex acoustic conditions such as noise and reverberation, further improving sound quality, clarity, resolution, and overall expressiveness. The Plus version places greater emphasis on synthesis quality and detail, making it suitable for professional scenarios that require higher sound quality, naturalness, and expressiveness, such as content creation, audiobooks, film and TV dubbing, brand voice design, and high-quality voice services.","typeHints":["tts"],"inputModalities":["text"],"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen-audio-3.1-asr-flash","name":"Qwen: Qwen-Audio-3.1-ASR-Flash","display_name":"Qwen: Qwen-Audio-3.1-ASR-Flash","type":"audio","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"],"output":["transcription"]},"cost":{"output":0.41},"limit":{"context":1000000,"output":1000000},"metadata":{"ownedBy":"qwen","created":1790664284,"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-asr-flash","name":"Qwen: Qwen3 ASR Flash","display_name":"Qwen: Qwen3 ASR Flash","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"knowledge":"2024-04","release_date":"2025-09-08","last_updated":"2025-09-08","open_weights":false,"modalities":{"input":["audio"],"output":["text"]},"cost":{"input":0.035,"output":0.035},"limit":{"context":53248,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-rerank","name":"Qwen: Qwen3 Rerank","display_name":"Qwen: Qwen3 Rerank","type":"rerank","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-02-01","last_updated":"2026-02-01","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.12,"output":0.12},"limit":{"context":32768,"output":8192},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"qwen/qwen3-vl-embedding","name":"Qwen: Qwen3 VL Embedding","display_name":"Qwen: Qwen3 VL Embedding","type":"embedding","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-02-05","last_updated":"2026-02-05","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.09,"output":0.09},"limit":{"context":32000,"output":4096},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3-vl-rerank","name":"Qwen: Qwen3 VL Rerank","display_name":"Qwen: Qwen3 VL Rerank","type":"rerank","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["text","image","video"],"output":["rerank"]},"cost":{"input":0.1,"output":0},"limit":{"context":1000000,"output":1000000},"metadata":{"ownedBy":"qwen","created":1781663333,"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3-vl-plus","name":"Qwen: Qwen3-VL-Plus","display_name":"Qwen: Qwen3-VL-Plus","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.2,"output":1.6},"limit":{"context":256000,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-flash","name":"Qwen: Qwen3.5-Flash","display_name":"Qwen: Qwen3.5-Flash","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":true,"tool_call":false,"release_date":"2026-02-23","last_updated":"2026-02-23","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"limit":{"context":991808,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.5-plus","name":"Qwen: Qwen3.5-Plus","display_name":"Qwen: Qwen3.5-Plus","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":true,"tool_call":false,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.4,"output":2.4,"cache_read":0.04},"limit":{"context":983616,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","display_name":"Qwen: Qwen3.6 Flash","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":true,"tool_call":false,"release_date":"2026-04-27","last_updated":"2026-04-27","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.19,"output":1.16,"cache_read":0.02,"cache_write":0.24},"limit":{"context":991808,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.6-plus","name":"Qwen: Qwen3.6-Plus","display_name":"Qwen: Qwen3.6-Plus","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.325,"output":1.95,"cache_read":0.0325,"cache_write":0.40625},"limit":{"context":991808,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"qwen/qwen3.7-flash","name":"Qwen: Qwen3.7-Flash","display_name":"Qwen: Qwen3.7-Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07-15","last_updated":"2026-07-15","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"limit":{"context":991808,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.7-max","name":"Qwen: Qwen3.7-Max","display_name":"Qwen: Qwen3.7-Max","type":"chat","attachment":false,"reasoning":{"supported":true},"temperature":true,"tool_call":true,"release_date":"2026-05-21","last_updated":"2026-05-21","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":2.5,"output":7.5,"cache_read":0.5},"limit":{"context":256000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.7-plus","name":"Qwen: Qwen3.7-Plus","display_name":"Qwen: Qwen3.7-Plus","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"limit":{"context":991808,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8-2.4T-A95B","display_name":"Qwen: Qwen3.8-2.4T-A95B","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-08-12","last_updated":"2026-08-12","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":262144,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8-27B","display_name":"Qwen: Qwen3.8-27B","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-08-14","last_updated":"2026-08-14","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.2,"output":2.5,"cache_read":0.05},"limit":{"context":262144,"output":32768},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3.8-flash","name":"Qwen: Qwen3.8-Flash","display_name":"Qwen: Qwen3.8-Flash","type":"chat","attachment":true,"reasoning":{"supported":true},"tool_call":true,"release_date":"2026-08-26","last_updated":"2026-08-26","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.113,"output":0.382,"cache_read":0.0141},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max","name":"Qwen: Qwen3.8-Max","display_name":"Qwen: Qwen3.8-Max","type":"chat","attachment":true,"reasoning":{"supported":true},"temperature":true,"tool_call":true,"release_date":"2026-08-03","last_updated":"2026-08-03","open_weights":false,"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"cost":{"input":1.65,"output":4.951,"cache_read":0.206},"limit":{"context":256000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"qwen/qwen3.8-max-0902","name":"Qwen: Qwen3.8-Max-0902","display_name":"Qwen: Qwen3.8-Max-0902","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-02","last_updated":"2026-09-02","open_weights":false,"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"limit":{"context":991808,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"qwen/qwen3.8-omni-flash","name":"Qwen: Qwen3.8-Omni-Flash","display_name":"Qwen: Qwen3.8-Omni-Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"release_date":"2026-09-17","last_updated":"2026-09-17","open_weights":false,"modalities":{"input":["text","image","audio","video"],"output":["text"]},"cost":{"input":0.15,"output":0.47,"cache_read":0.016},"limit":{"context":991808,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"sakana/fugu-ultra-v2","name":"SakanaAI:Fugu Ultra v2","display_name":"SakanaAI:Fugu Ultra v2","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":false,"tool_call":true,"knowledge":"2026-08-28","release_date":"2026-09-11","last_updated":"2026-09-11","open_weights":false,"modalities":{"input":["text","image","pdf"],"output":["text"]},"cost":{"input":5,"output":30,"cache_read":0.5},"limit":{"context":1000000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"sapiens-ai/agnes-2.5-flash","name":"Sapiens AI: Agnes 2.5 Flash","display_name":"Sapiens AI: Agnes 2.5 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07","last_updated":"2026-07","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0,"output":0},"limit":{"context":512000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"sapiens-ai/agnes-2.5-pro","name":"Sapiens AI: Agnes 2.5 Pro","display_name":"Sapiens AI: Agnes 2.5 Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07-24","last_updated":"2026-07-24","open_weights":true,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":0.45,"output":0.9,"cache_read":0.0038},"limit":{"context":1000000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":true,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"continuation":["thinking_blocks"],"interleaved":true,"summaries":true,"visibility":"summary"}}},{"id":"stepfun/step-3.5-flash","name":"StepFun: Step 3.5 Flash","display_name":"StepFun: Step 3.5 Flash","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.1,"output":0.3},"limit":{"context":262144,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"stepfun/step-3.7-flash","name":"StepFun: Step 3.7 Flash","display_name":"StepFun: Step 3.7 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"limit":{"context":256000,"output":230400},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"stepfun/step-5-preview","name":"StepFun: Step 5 Preview","display_name":"StepFun: Step 5 Preview","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"tool_call":true,"release_date":"2026-09-16","last_updated":"2026-09-20","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":1,"output":2.7,"cache_read":0.05},"limit":{"context":1000000,"output":1000000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"tencent/hy3","name":"Tencent: Hy3","display_name":"Tencent: Hy3","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07-06","last_updated":"2026-07-06","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.13,"output":0.53,"cache_read":0.033},"limit":{"context":262144,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"tencent/hy4-preview","name":"Tencent: Hy4 Preview","display_name":"Tencent: Hy4 Preview","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-08-28","last_updated":"2026-08-28","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.834,"output":2.501,"cache_read":0.042},"limit":{"context":1048576,"output":64000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.2-fast","name":"xAI: Grok 4.2 Fast","display_name":"xAI: Grok 4.2 Fast","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"release_date":"2026-03-09","last_updated":"2026-03-09","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":2000000,"output":30000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"x-ai/grok-4.2-fast-non-reasoning","name":"xAI: Grok 4.2 Fast Non Reasoning","display_name":"xAI: Grok 4.2 Fast Non Reasoning","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"release_date":"2026-03-09","last_updated":"2026-03-09","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.2},"limit":{"context":2000000,"output":30000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"x-ai/grok-4.3","name":"xAI: Grok 4.3","display_name":"xAI: Grok 4.3","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-04-17","last_updated":"2026-04-17","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"limit":{"context":1000000,"output":900000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.5","name":"xAI: Grok 4.5","display_name":"xAI: Grok 4.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-07-08","last_updated":"2026-07-08","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.3},"limit":{"context":500000,"output":450000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.6","name":"xAI: Grok 4.6","display_name":"xAI: Grok 4.6","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.5},"limit":{"context":500000,"output":450000},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-4.7","name":"xAI: Grok 4.7","display_name":"xAI: Grok 4.7","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2026-05","release_date":"2026-09-21","last_updated":"2026-09-21","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":2,"output":6,"cache_read":0.5},"limit":{"context":500000,"output":500000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"x-ai/grok-build-0.1","name":"xAI: Grok Build 0.1","display_name":"xAI: Grok Build 0.1","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-04-16","last_updated":"2026-04-16","open_weights":false,"modalities":{"input":["text","image"],"output":["text"]},"cost":{"input":1,"output":2,"cache_read":0.2},"limit":{"context":256000,"output":230400},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"x-ai/grok-voice-stt-1.0","name":"xAI: Grok Voice STT 1.0","display_name":"xAI: Grok Voice STT 1.0","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-08-04","last_updated":"2026-08-04","open_weights":false,"modalities":{"input":["audio"],"output":["text"]},"limit":{"context":15000,"output":15000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"x-ai/grok-voice-tts-1.0","name":"xAI: Grok Voice TTS 1.0","display_name":"xAI: Grok Voice TTS 1.0","type":"audio","attachment":false,"reasoning":{"supported":false},"temperature":false,"tool_call":false,"release_date":"2026-07-31","last_updated":"2026-07-31","open_weights":false,"modalities":{"input":["text"],"output":["audio"]},"limit":{"context":15000,"output":15000},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","display_name":"Xiaomi: MiMo-V2.5","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","open_weights":true,"modalities":{"input":["text","image","audio","video"],"output":["text"]},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"xiaomi/mimo-v2.5-asr","name":"Xiaomi: MiMo-V2.5-ASR","display_name":"Xiaomi: MiMo-V2.5-ASR","type":"chat","reasoning":{"supported":false},"tool_call":false,"modalities":{"input":["audio"],"output":["transcription"]},"limit":{"context":1024,"output":1024},"metadata":{"ownedBy":"xiaomi","created":1783426188,"source":"public-provider-conf"},"vision":false},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","display_name":"Xiaomi: MiMo-V2.5-Pro","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","display_name":"Xiaomi: MiMo-V2.6-Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":true,"modalities":{"input":["text","image","audio","video"],"output":["text"]},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"xiaomi/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","display_name":"Xiaomi: MiMo-V2.6-Pro","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-22","last_updated":"2026-09-22","open_weights":true,"modalities":{"input":["text","image","audio","video"],"output":["text"]},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","display_name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-21","last_updated":"2026-09-21","open_weights":true,"modalities":{"input":["text","image","audio","video"],"output":["text"]},"cost":{"input":4.35,"output":8.7,"cache_read":0.036,"cache_write":0},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"z-ai/glm-4.5","name":"Z.AI: GLM 4.5","display_name":"Z.AI: GLM 4.5","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.3,"output":1.3,"cache_read":0.15},"limit":{"context":128000,"output":65536},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"z-ai/glm-4.5-air","name":"Z.AI: GLM 4.5 Air","display_name":"Z.AI: GLM 4.5 Air","type":"chat","attachment":false,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.12,"output":0.8,"cache_read":0.06},"limit":{"context":128000,"output":98304},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"z-ai/glm-4.6","name":"Z.AI: GLM 4.6","display_name":"Z.AI: GLM 4.6","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.5,"output":2,"cache_read":0.1},"limit":{"context":200000,"output":65535},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.6v","name":"Z.AI: GLM 4.6V","display_name":"Z.AI: GLM 4.6V","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":false,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.3,"output":0.9,"cache_read":0.15},"limit":{"context":128000,"output":24000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"z-ai/glm-4.6v-flash-free","name":"Z.AI: GLM 4.6V Flash (Free)","display_name":"Z.AI: GLM 4.6V Flash (Free)","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2025-12-08","last_updated":"2025-12-08","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.0218,"output":0.2184,"cache_read":0.0044},"limit":{"context":200000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"z-ai/glm-4.6v-flash","name":"Z.AI: GLM 4.6V FlashX","display_name":"Z.AI: GLM 4.6V FlashX","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2025-12-08","last_updated":"2025-12-08","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.0218,"output":0.2184,"cache_read":0.0044},"limit":{"context":200000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"z-ai/glm-4.7","name":"Z.AI: GLM 4.7","display_name":"Z.AI: GLM 4.7","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.4004,"output":1.9292,"cache_read":0.08008},"limit":{"context":200000,"output":65535},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-4.7-flash-free","name":"Z.AI: GLM 4.7 Flash (Free)","display_name":"Z.AI: GLM 4.7 Flash (Free)","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.07,"output":0.4,"cache_read":0.01},"limit":{"context":200000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-4.7-flashx","name":"Z.AI: GLM 4.7 FlashX","display_name":"Z.AI: GLM 4.7 FlashX","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.0728,"output":0.4367,"cache_read":0.0146},"limit":{"context":200000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"interleaved":{"field":"reasoning_content"},"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5","name":"Z.AI: GLM 5","display_name":"Z.AI: GLM 5","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-02-12","last_updated":"2026-02-12","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.6,"output":1.9,"cache_read":0.1},"limit":{"context":200000,"output":128000},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true,"interleaved":true,"summaries":true,"visibility":"summary","continuation":["thinking_blocks"]}}},{"id":"z-ai/glm-5-turbo","name":"Z.AI: GLM 5 Turbo","display_name":"Z.AI: GLM 5 Turbo","type":"chat","attachment":false,"reasoning":{"supported":true},"temperature":true,"tool_call":true,"release_date":"2026-03-16","last_updated":"2026-03-16","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":1.2,"output":4,"cache_read":0.24},"limit":{"context":202800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.1","name":"Z.AI: GLM 5.1","display_name":"Z.AI: GLM 5.1","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-04-07","last_updated":"2026-04-07","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.7,"output":2.5,"cache_read":0.18},"limit":{"context":200000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.2","name":"Z.AI: GLM 5.2","display_name":"Z.AI: GLM 5.2","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-06-13","last_updated":"2026-06-13","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.189,"output":0.594,"cache_read":0.0351},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3","name":"Z.AI: GLM 5.3","display_name":"Z.AI: GLM 5.3","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-08-14","last_updated":"2026-08-14","open_weights":true,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":0.6,"output":1.1,"cache_read":0.2},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flash","name":"Z.AI: GLM 5.3 Flash","display_name":"Z.AI: GLM 5.3 Flash","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-08-26","last_updated":"2026-08-26","open_weights":true,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.1,"output":0.3,"cache_read":0.025},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true,"extra_capabilities":{"reasoning":{"supported":true}}},{"id":"z-ai/glm-5.3-flashx","name":"Z.AI: GLM 5.3 FlashX","display_name":"Z.AI: GLM 5.3 FlashX","type":"chat","attachment":true,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-18","last_updated":"2026-09-18","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":0.37,"output":1.25,"cache_read":0.09},"limit":{"context":1048576,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true},{"id":"z-ai/glm-5.3-prime","name":"Z.AI: GLM 5.3 Prime","display_name":"Z.AI: GLM 5.3 Prime","type":"chat","attachment":false,"reasoning":{"supported":true,"default":true},"temperature":true,"tool_call":true,"release_date":"2026-09-23","last_updated":"2026-09-23","open_weights":false,"modalities":{"input":["text"],"output":["text"]},"cost":{"input":2.8,"output":8.8,"cache_read":0.56},"limit":{"context":1000000,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":false},{"id":"z-ai/glm-5v-turbo","name":"Z.AI: GLM 5V Turbo","display_name":"Z.AI: GLM 5V Turbo","type":"chat","attachment":true,"reasoning":{"supported":false},"temperature":true,"tool_call":true,"release_date":"2026-04-01","last_updated":"2026-04-01","open_weights":false,"modalities":{"input":["text","image","video"],"output":["text"]},"cost":{"input":1.2,"output":4,"cache_read":0.24},"limit":{"context":202800,"output":131072},"metadata":{"source":"public-provider-conf"},"vision":true}],"metadata":{"source":"public-provider-conf"}}},"updated_at":"2026-10-18T20:13:15.870Z"}